| 2 2 2 31 31 31 31 31 1 31 1 1 12 12 12 1 12 1 12 55 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. */ #include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/mpage.h> #include <linux/fs.h> #include <linux/writeback.h> #include <linux/swap.h> #include <linux/gfs2_ondisk.h> #include <linux/backing-dev.h> #include <linux/uio.h> #include <trace/events/writeback.h> #include <linux/sched/signal.h> #include "gfs2.h" #include "incore.h" #include "bmap.h" #include "glock.h" #include "inode.h" #include "log.h" #include "meta_io.h" #include "quota.h" #include "trans.h" #include "rgrp.h" #include "super.h" #include "util.h" #include "glops.h" #include "aops.h" void gfs2_trans_add_databufs(struct gfs2_inode *ip, struct folio *folio, size_t from, size_t len) { struct buffer_head *head = folio_buffers(folio); unsigned int bsize = head->b_size; struct buffer_head *bh; size_t to = from + len; size_t start, end; for (bh = head, start = 0; bh != head || !start; bh = bh->b_this_page, start = end) { end = start + bsize; if (end <= from) continue; if (start >= to) break; set_buffer_uptodate(bh); gfs2_trans_add_data(ip->i_gl, bh); } } /** * gfs2_get_block_noalloc - Fills in a buffer head with details about a block * @inode: The inode * @lblock: The block number to look up * @bh_result: The buffer head to return the result in * @create: Non-zero if we may add block to the file * * Returns: errno */ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, struct buffer_head *bh_result, int create) { int error; error = gfs2_block_map(inode, lblock, bh_result, 0); if (error) return error; if (!buffer_mapped(bh_result)) return -ENODATA; return 0; } /** * gfs2_write_jdata_folio - gfs2 jdata-specific version of block_write_full_folio * @folio: The folio to write * @wbc: The writeback control * * This is the same as calling block_write_full_folio, but it also * writes pages outside of i_size */ static int gfs2_write_jdata_folio(struct folio *folio, struct writeback_control *wbc) { struct inode * const inode = folio->mapping->host; loff_t i_size = i_size_read(inode); /* * The folio straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ if (folio_pos(folio) < i_size && i_size < folio_pos(folio) + folio_size(folio)) folio_zero_segment(folio, offset_in_folio(folio, i_size), folio_size(folio)); return __block_write_full_folio(inode, folio, gfs2_get_block_noalloc, wbc); } /** * __gfs2_jdata_write_folio - The core of jdata writepage * @folio: The folio to write * @wbc: The writeback control * * Implements the core of write back. If a transaction is required then * the checked flag will have been set and the transaction will have * already been started before this is called. */ static int __gfs2_jdata_write_folio(struct folio *folio, struct writeback_control *wbc) { struct inode *inode = folio->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); if (folio_test_checked(folio)) { folio_clear_checked(folio); if (!folio_buffers(folio)) { create_empty_buffers(folio, inode->i_sb->s_blocksize, BIT(BH_Dirty)|BIT(BH_Uptodate)); } gfs2_trans_add_databufs(ip, folio, 0, folio_size(folio)); } return gfs2_write_jdata_folio(folio, wbc); } /** * gfs2_jdata_writepage - Write complete page * @page: Page to write * @wbc: The writeback control * * Returns: errno * */ static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc) { struct folio *folio = page_folio(page); struct inode *inode = page->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); if (gfs2_assert_withdraw(sdp, ip->i_gl->gl_state == LM_ST_EXCLUSIVE)) goto out; if (folio_test_checked(folio) || current->journal_info) goto out_ignore; return __gfs2_jdata_write_folio(folio, wbc); out_ignore: folio_redirty_for_writepage(wbc, folio); out: folio_unlock(folio); return 0; } /** * gfs2_writepages - Write a bunch of dirty pages back to disk * @mapping: The mapping to write * @wbc: Write-back control * * Used for both ordered and writeback modes. */ static int gfs2_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping); struct iomap_writepage_ctx wpc = { }; int ret; /* * Even if we didn't write enough pages here, we might still be holding * dirty pages in the ail. We forcibly flush the ail because we don't * want balance_dirty_pages() to loop indefinitely trying to write out * pages held in the ail that it can't find. */ ret = iomap_writepages(mapping, wbc, &wpc, &gfs2_writeback_ops); if (ret == 0 && wbc->nr_to_write > 0) set_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags); return ret; } /** * gfs2_write_jdata_batch - Write back a folio batch's worth of folios * @mapping: The mapping * @wbc: The writeback control * @fbatch: The batch of folios * @done_index: Page index * * Returns: non-zero if loop should terminate, zero otherwise */ static int gfs2_write_jdata_batch(struct address_space *mapping, struct writeback_control *wbc, struct folio_batch *fbatch, pgoff_t *done_index) { struct inode *inode = mapping->host; struct gfs2_sbd *sdp = GFS2_SB(inode); unsigned nrblocks; int i; int ret; size_t size = 0; int nr_folios = folio_batch_count(fbatch); for (i = 0; i < nr_folios; i++) size += folio_size(fbatch->folios[i]); nrblocks = size >> inode->i_blkbits; ret = gfs2_trans_begin(sdp, nrblocks, nrblocks); if (ret < 0) return ret; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch->folios[i]; *done_index = folio->index; folio_lock(folio); if (unlikely(folio->mapping != mapping)) { continue_unlock: folio_unlock(folio); continue; } if (!folio_test_dirty(folio)) { /* someone wrote it for us */ goto continue_unlock; } if (folio_test_writeback(folio)) { if (wbc->sync_mode != WB_SYNC_NONE) folio_wait_writeback(folio); else goto continue_unlock; } BUG_ON(folio_test_writeback(folio)); if (!folio_clear_dirty_for_io(folio)) goto continue_unlock; trace_wbc_writepage(wbc, inode_to_bdi(inode)); ret = __gfs2_jdata_write_folio(folio, wbc); if (unlikely(ret)) { if (ret == AOP_WRITEPAGE_ACTIVATE) { folio_unlock(folio); ret = 0; } else { /* * done_index is set past this page, * so media errors will not choke * background writeout for the entire * file. This has consequences for * range_cyclic semantics (ie. it may * not be suitable for data integrity * writeout). */ *done_index = folio_next_index(folio); ret = 1; break; } } /* * We stop writing back only if we are not doing * integrity sync. In case of integrity sync we have to * keep going until we have written all the pages * we tagged for writeback prior to entering this loop. */ if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) { ret = 1; break; } } gfs2_trans_end(sdp); return ret; } /** * gfs2_write_cache_jdata - Like write_cache_pages but different * @mapping: The mapping to write * @wbc: The writeback control * * The reason that we use our own function here is that we need to * start transactions before we grab page locks. This allows us * to get the ordering right. */ static int gfs2_write_cache_jdata(struct address_space *mapping, struct writeback_control *wbc) { int ret = 0; int done = 0; struct folio_batch fbatch; int nr_folios; pgoff_t writeback_index; pgoff_t index; pgoff_t end; pgoff_t done_index; int cycled; int range_whole = 0; xa_mark_t tag; folio_batch_init(&fbatch); if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; /* prev offset */ index = writeback_index; if (index == 0) cycled = 1; else cycled = 0; end = -1; } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ } if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, index, end); done_index = index; while (!done && (index <= end)) { nr_folios = filemap_get_folios_tag(mapping, &index, end, tag, &fbatch); if (nr_folios == 0) break; ret = gfs2_write_jdata_batch(mapping, wbc, &fbatch, &done_index); if (ret) done = 1; if (ret > 0) ret = 0; folio_batch_release(&fbatch); cond_resched(); } if (!cycled && !done) { /* * range_cyclic: * We hit the last page and there is more work to be done: wrap * back to the start of the file */ cycled = 1; index = 0; end = writeback_index - 1; goto retry; } if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; return ret; } /** * gfs2_jdata_writepages - Write a bunch of dirty pages back to disk * @mapping: The mapping to write * @wbc: The writeback control * */ static int gfs2_jdata_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct gfs2_inode *ip = GFS2_I(mapping->host); struct gfs2_sbd *sdp = GFS2_SB(mapping->host); int ret; ret = gfs2_write_cache_jdata(mapping, wbc); if (ret == 0 && wbc->sync_mode == WB_SYNC_ALL) { gfs2_log_flush(sdp, ip->i_gl, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_JDATA_WPAGES); ret = gfs2_write_cache_jdata(mapping, wbc); } return ret; } /** * stuffed_read_folio - Fill in a Linux folio with stuffed file data * @ip: the inode * @folio: the folio * * Returns: errno */ static int stuffed_read_folio(struct gfs2_inode *ip, struct folio *folio) { struct buffer_head *dibh = NULL; size_t dsize = i_size_read(&ip->i_inode); void *from = NULL; int error = 0; /* * Due to the order of unstuffing files and ->fault(), we can be * asked for a zero folio in the case of a stuffed file being extended, * so we need to supply one here. It doesn't happen often. */ if (unlikely(folio->index)) { dsize = 0; } else { error = gfs2_meta_inode_buffer(ip, &dibh); if (error) goto out; from = dibh->b_data + sizeof(struct gfs2_dinode); } folio_fill_tail(folio, 0, from, dsize); brelse(dibh); out: folio_end_read(folio, error == 0); return error; } /** * gfs2_read_folio - read a folio from a file * @file: The file to read * @folio: The folio in the file */ static int gfs2_read_folio(struct file *file, struct folio *folio) { struct inode *inode = folio->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); int error; if (!gfs2_is_jdata(ip) || (i_blocksize(inode) == PAGE_SIZE && !folio_buffers(folio))) { error = iomap_read_folio(folio, &gfs2_iomap_ops); } else if (gfs2_is_stuffed(ip)) { error = stuffed_read_folio(ip, folio); } else { error = mpage_read_folio(folio, gfs2_block_map); } if (gfs2_withdrawing_or_withdrawn(sdp)) return -EIO; return error; } /** * gfs2_internal_read - read an internal file * @ip: The gfs2 inode * @buf: The buffer to fill * @pos: The file position * @size: The amount to read * */ ssize_t gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, size_t size) { struct address_space *mapping = ip->i_inode.i_mapping; unsigned long index = *pos >> PAGE_SHIFT; size_t copied = 0; do { size_t offset, chunk; struct folio *folio; folio = read_cache_folio(mapping, index, gfs2_read_folio, NULL); if (IS_ERR(folio)) { if (PTR_ERR(folio) == -EINTR) continue; return PTR_ERR(folio); } offset = *pos + copied - folio_pos(folio); chunk = min(size - copied, folio_size(folio) - offset); memcpy_from_folio(buf + copied, folio, offset, chunk); index = folio_next_index(folio); folio_put(folio); copied += chunk; } while(copied < size); (*pos) += size; return size; } /** * gfs2_readahead - Read a bunch of pages at once * @rac: Read-ahead control structure * * Some notes: * 1. This is only for readahead, so we can simply ignore any things * which are slightly inconvenient (such as locking conflicts between * the page lock and the glock) and return having done no I/O. Its * obviously not something we'd want to do on too regular a basis. * Any I/O we ignore at this time will be done via readpage later. * 2. We don't handle stuffed files here we let readpage do the honours. * 3. mpage_readahead() does most of the heavy lifting in the common case. * 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places. */ static void gfs2_readahead(struct readahead_control *rac) { struct inode *inode = rac->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); if (gfs2_is_stuffed(ip)) ; else if (gfs2_is_jdata(ip)) mpage_readahead(rac, gfs2_block_map); else iomap_readahead(rac, &gfs2_iomap_ops); } /** * adjust_fs_space - Adjusts the free space available due to gfs2_grow * @inode: the rindex inode */ void adjust_fs_space(struct inode *inode) { struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master; struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local; struct buffer_head *m_bh; u64 fs_total, new_free; if (gfs2_trans_begin(sdp, 2 * RES_STATFS, 0) != 0) return; /* Total up the file system space, according to the latest rindex. */ fs_total = gfs2_ri_total(sdp); if (gfs2_meta_inode_buffer(m_ip, &m_bh) != 0) goto out; spin_lock(&sdp->sd_statfs_spin); gfs2_statfs_change_in(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode)); if (fs_total > (m_sc->sc_total + l_sc->sc_total)) new_free = fs_total - (m_sc->sc_total + l_sc->sc_total); else new_free = 0; spin_unlock(&sdp->sd_statfs_spin); fs_warn(sdp, "File system extended by %llu blocks.\n", (unsigned long long)new_free); gfs2_statfs_change(sdp, new_free, new_free, 0); update_statfs(sdp, m_bh); brelse(m_bh); out: sdp->sd_rindex_uptodate = 0; gfs2_trans_end(sdp); } static bool jdata_dirty_folio(struct address_space *mapping, struct folio *folio) { if (current->journal_info) folio_set_checked(folio); return block_dirty_folio(mapping, folio); } /** * gfs2_bmap - Block map function * @mapping: Address space info * @lblock: The block to map * * Returns: The disk address for the block or 0 on hole or error */ static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock) { struct gfs2_inode *ip = GFS2_I(mapping->host); struct gfs2_holder i_gh; sector_t dblock = 0; int error; error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh); if (error) return 0; if (!gfs2_is_stuffed(ip)) dblock = iomap_bmap(mapping, lblock, &gfs2_iomap_ops); gfs2_glock_dq_uninit(&i_gh); return dblock; } static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh) { struct gfs2_bufdata *bd; lock_buffer(bh); gfs2_log_lock(sdp); clear_buffer_dirty(bh); bd = bh->b_private; if (bd) { if (!list_empty(&bd->bd_list) && !buffer_pinned(bh)) list_del_init(&bd->bd_list); else { spin_lock(&sdp->sd_ail_lock); gfs2_remove_from_journal(bh, REMOVE_JDATA); spin_unlock(&sdp->sd_ail_lock); } } bh->b_bdev = NULL; clear_buffer_mapped(bh); clear_buffer_req(bh); clear_buffer_new(bh); gfs2_log_unlock(sdp); unlock_buffer(bh); } static void gfs2_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct gfs2_sbd *sdp = GFS2_SB(folio->mapping->host); size_t stop = offset + length; int partial_page = (offset || length < folio_size(folio)); struct buffer_head *bh, *head; unsigned long pos = 0; BUG_ON(!folio_test_locked(folio)); if (!partial_page) folio_clear_checked(folio); head = folio_buffers(folio); if (!head) goto out; bh = head; do { if (pos + bh->b_size > stop) return; if (offset <= pos) gfs2_discard(sdp, bh); pos += bh->b_size; bh = bh->b_this_page; } while (bh != head); out: if (!partial_page) filemap_release_folio(folio, 0); } /** * gfs2_release_folio - free the metadata associated with a folio * @folio: the folio that's being released * @gfp_mask: passed from Linux VFS, ignored by us * * Calls try_to_free_buffers() to free the buffers and put the folio if the * buffers can be released. * * Returns: true if the folio was put or else false */ bool gfs2_release_folio(struct folio *folio, gfp_t gfp_mask) { struct address_space *mapping = folio->mapping; struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping); struct buffer_head *bh, *head; struct gfs2_bufdata *bd; head = folio_buffers(folio); if (!head) return false; /* * mm accommodates an old ext3 case where clean folios might * not have had the dirty bit cleared. Thus, it can send actual * dirty folios to ->release_folio() via shrink_active_list(). * * As a workaround, we skip folios that contain dirty buffers * below. Once ->release_folio isn't called on dirty folios * anymore, we can warn on dirty buffers like we used to here * again. */ gfs2_log_lock(sdp); bh = head; do { if (atomic_read(&bh->b_count)) goto cannot_release; bd = bh->b_private; if (bd && bd->bd_tr) goto cannot_release; if (buffer_dirty(bh) || WARN_ON(buffer_pinned(bh))) goto cannot_release; bh = bh->b_this_page; } while (bh != head); bh = head; do { bd = bh->b_private; if (bd) { gfs2_assert_warn(sdp, bd->bd_bh == bh); bd->bd_bh = NULL; bh->b_private = NULL; /* * The bd may still be queued as a revoke, in which * case we must not dequeue nor free it. */ if (!bd->bd_blkno && !list_empty(&bd->bd_list)) list_del_init(&bd->bd_list); if (list_empty(&bd->bd_list)) kmem_cache_free(gfs2_bufdata_cachep, bd); } bh = bh->b_this_page; } while (bh != head); gfs2_log_unlock(sdp); return try_to_free_buffers(folio); cannot_release: gfs2_log_unlock(sdp); return false; } static const struct address_space_operations gfs2_aops = { .writepages = gfs2_writepages, .read_folio = gfs2_read_folio, .readahead = gfs2_readahead, .dirty_folio = iomap_dirty_folio, .release_folio = iomap_release_folio, .invalidate_folio = iomap_invalidate_folio, .bmap = gfs2_bmap, .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, }; static const struct address_space_operations gfs2_jdata_aops = { .writepage = gfs2_jdata_writepage, .writepages = gfs2_jdata_writepages, .read_folio = gfs2_read_folio, .readahead = gfs2_readahead, .dirty_folio = jdata_dirty_folio, .bmap = gfs2_bmap, .migrate_folio = buffer_migrate_folio, .invalidate_folio = gfs2_invalidate_folio, .release_folio = gfs2_release_folio, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, }; void gfs2_set_aops(struct inode *inode) { if (gfs2_is_jdata(GFS2_I(inode))) inode->i_mapping->a_ops = &gfs2_jdata_aops; else inode->i_mapping->a_ops = &gfs2_aops; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TTY_FLIP_H #define _LINUX_TTY_FLIP_H #include <linux/tty_buffer.h> #include <linux/tty_port.h> struct tty_ldisc; int tty_buffer_set_limit(struct tty_port *port, int limit); unsigned int tty_buffer_space_avail(struct tty_port *port); int tty_buffer_request_room(struct tty_port *port, size_t size); size_t __tty_insert_flip_string_flags(struct tty_port *port, const u8 *chars, const u8 *flags, bool mutable_flags, size_t size); size_t tty_prepare_flip_string(struct tty_port *port, u8 **chars, size_t size); void tty_flip_buffer_push(struct tty_port *port); /** * tty_insert_flip_string_fixed_flag - add characters to the tty buffer * @port: tty port * @chars: characters * @flag: flag value for each character * @size: size * * Queue a series of bytes to the tty buffering. All the characters passed are * marked with the supplied flag. * * Returns: the number added. */ static inline size_t tty_insert_flip_string_fixed_flag(struct tty_port *port, const u8 *chars, u8 flag, size_t size) { return __tty_insert_flip_string_flags(port, chars, &flag, false, size); } /** * tty_insert_flip_string_flags - add characters to the tty buffer * @port: tty port * @chars: characters * @flags: flag bytes * @size: size * * Queue a series of bytes to the tty buffering. For each character the flags * array indicates the status of the character. * * Returns: the number added. */ static inline size_t tty_insert_flip_string_flags(struct tty_port *port, const u8 *chars, const u8 *flags, size_t size) { return __tty_insert_flip_string_flags(port, chars, flags, true, size); } /** * tty_insert_flip_char - add one character to the tty buffer * @port: tty port * @ch: character * @flag: flag byte * * Queue a single byte @ch to the tty buffering, with an optional flag. */ static inline size_t tty_insert_flip_char(struct tty_port *port, u8 ch, u8 flag) { struct tty_buffer *tb = port->buf.tail; int change; change = !tb->flags && (flag != TTY_NORMAL); if (!change && tb->used < tb->size) { if (tb->flags) *flag_buf_ptr(tb, tb->used) = flag; *char_buf_ptr(tb, tb->used++) = ch; return 1; } return __tty_insert_flip_string_flags(port, &ch, &flag, false, 1); } static inline size_t tty_insert_flip_string(struct tty_port *port, const u8 *chars, size_t size) { return tty_insert_flip_string_fixed_flag(port, chars, TTY_NORMAL, size); } size_t tty_ldisc_receive_buf(struct tty_ldisc *ld, const u8 *p, const u8 *f, size_t count); void tty_buffer_lock_exclusive(struct tty_port *port); void tty_buffer_unlock_exclusive(struct tty_port *port); #endif /* _LINUX_TTY_FLIP_H */ |
| 28 8 8 23 20 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 | /* * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README */ /* Reiserfs block (de)allocator, bitmap-based. */ #include <linux/time.h> #include "reiserfs.h" #include <linux/errno.h> #include <linux/buffer_head.h> #include <linux/kernel.h> #include <linux/pagemap.h> #include <linux/vmalloc.h> #include <linux/quotaops.h> #include <linux/seq_file.h> #define PREALLOCATION_SIZE 9 /* different reiserfs block allocator options */ #define SB_ALLOC_OPTS(s) (REISERFS_SB(s)->s_alloc_options.bits) #define _ALLOC_concentrating_formatted_nodes 0 #define _ALLOC_displacing_large_files 1 #define _ALLOC_displacing_new_packing_localities 2 #define _ALLOC_old_hashed_relocation 3 #define _ALLOC_new_hashed_relocation 4 #define _ALLOC_skip_busy 5 #define _ALLOC_displace_based_on_dirid 6 #define _ALLOC_hashed_formatted_nodes 7 #define _ALLOC_old_way 8 #define _ALLOC_hundredth_slices 9 #define _ALLOC_dirid_groups 10 #define _ALLOC_oid_groups 11 #define _ALLOC_packing_groups 12 #define concentrating_formatted_nodes(s) test_bit(_ALLOC_concentrating_formatted_nodes, &SB_ALLOC_OPTS(s)) #define displacing_large_files(s) test_bit(_ALLOC_displacing_large_files, &SB_ALLOC_OPTS(s)) #define displacing_new_packing_localities(s) test_bit(_ALLOC_displacing_new_packing_localities, &SB_ALLOC_OPTS(s)) #define SET_OPTION(optname) \ do { \ reiserfs_info(s, "block allocator option \"%s\" is set", #optname); \ set_bit(_ALLOC_ ## optname , &SB_ALLOC_OPTS(s)); \ } while(0) #define TEST_OPTION(optname, s) \ test_bit(_ALLOC_ ## optname , &SB_ALLOC_OPTS(s)) static inline void get_bit_address(struct super_block *s, b_blocknr_t block, unsigned int *bmap_nr, unsigned int *offset) { /* * It is in the bitmap block number equal to the block * number divided by the number of bits in a block. */ *bmap_nr = block >> (s->s_blocksize_bits + 3); /* Within that bitmap block it is located at bit offset *offset. */ *offset = block & ((s->s_blocksize << 3) - 1); } int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value) { unsigned int bmap, offset; unsigned int bmap_count = reiserfs_bmap_count(s); if (block == 0 || block >= SB_BLOCK_COUNT(s)) { reiserfs_error(s, "vs-4010", "block number is out of range %lu (%u)", block, SB_BLOCK_COUNT(s)); return 0; } get_bit_address(s, block, &bmap, &offset); /* * Old format filesystem? Unlikely, but the bitmaps are all * up front so we need to account for it. */ if (unlikely(test_bit(REISERFS_OLD_FORMAT, &REISERFS_SB(s)->s_properties))) { b_blocknr_t bmap1 = REISERFS_SB(s)->s_sbh->b_blocknr + 1; if (block >= bmap1 && block <= bmap1 + bmap_count) { reiserfs_error(s, "vs-4019", "bitmap block %lu(%u) " "can't be freed or reused", block, bmap_count); return 0; } } else { if (offset == 0) { reiserfs_error(s, "vs-4020", "bitmap block %lu(%u) " "can't be freed or reused", block, bmap_count); return 0; } } if (bmap >= bmap_count) { reiserfs_error(s, "vs-4030", "bitmap for requested block " "is out of range: block=%lu, bitmap_nr=%u", block, bmap); return 0; } if (bit_value == 0 && block == SB_ROOT_BLOCK(s)) { reiserfs_error(s, "vs-4050", "this is root block (%u), " "it must be busy", SB_ROOT_BLOCK(s)); return 0; } return 1; } /* * Searches in journal structures for a given block number (bmap, off). * If block is found in reiserfs journal it suggests next free block * candidate to test. */ static inline int is_block_in_journal(struct super_block *s, unsigned int bmap, int off, int *next) { b_blocknr_t tmp; if (reiserfs_in_journal(s, bmap, off, 1, &tmp)) { if (tmp) { /* hint supplied */ *next = tmp; PROC_INFO_INC(s, scan_bitmap.in_journal_hint); } else { (*next) = off + 1; /* inc offset to avoid looping. */ PROC_INFO_INC(s, scan_bitmap.in_journal_nohint); } PROC_INFO_INC(s, scan_bitmap.retry); return 1; } return 0; } /* * Searches for a window of zero bits with given minimum and maximum * lengths in one bitmap block */ static int scan_bitmap_block(struct reiserfs_transaction_handle *th, unsigned int bmap_n, int *beg, int boundary, int min, int max, int unfm) { struct super_block *s = th->t_super; struct reiserfs_bitmap_info *bi = &SB_AP_BITMAP(s)[bmap_n]; struct buffer_head *bh; int end, next; int org = *beg; BUG_ON(!th->t_trans_id); RFALSE(bmap_n >= reiserfs_bmap_count(s), "Bitmap %u is out of " "range (0..%u)", bmap_n, reiserfs_bmap_count(s) - 1); PROC_INFO_INC(s, scan_bitmap.bmap); if (!bi) { reiserfs_error(s, "jdm-4055", "NULL bitmap info pointer " "for bitmap %d", bmap_n); return 0; } bh = reiserfs_read_bitmap_block(s, bmap_n); if (bh == NULL) return 0; while (1) { cont: if (bi->free_count < min) { brelse(bh); return 0; /* No free blocks in this bitmap */ } /* search for a first zero bit -- beginning of a window */ *beg = reiserfs_find_next_zero_le_bit ((unsigned long *)(bh->b_data), boundary, *beg); /* * search for a zero bit fails or the rest of bitmap block * cannot contain a zero window of minimum size */ if (*beg + min > boundary) { brelse(bh); return 0; } if (unfm && is_block_in_journal(s, bmap_n, *beg, beg)) continue; /* first zero bit found; we check next bits */ for (end = *beg + 1;; end++) { if (end >= *beg + max || end >= boundary || reiserfs_test_le_bit(end, bh->b_data)) { next = end; break; } /* * finding the other end of zero bit window requires * looking into journal structures (in case of * searching for free blocks for unformatted nodes) */ if (unfm && is_block_in_journal(s, bmap_n, end, &next)) break; } /* * now (*beg) points to beginning of zero bits window, * (end) points to one bit after the window end */ /* found window of proper size */ if (end - *beg >= min) { int i; reiserfs_prepare_for_journal(s, bh, 1); /* * try to set all blocks used checking are * they still free */ for (i = *beg; i < end; i++) { /* Don't check in journal again. */ if (reiserfs_test_and_set_le_bit (i, bh->b_data)) { /* * bit was set by another process while * we slept in prepare_for_journal() */ PROC_INFO_INC(s, scan_bitmap.stolen); /* * we can continue with smaller set * of allocated blocks, if length of * this set is more or equal to `min' */ if (i >= *beg + min) { end = i; break; } /* * otherwise we clear all bit * were set ... */ while (--i >= *beg) reiserfs_clear_le_bit (i, bh->b_data); reiserfs_restore_prepared_buffer(s, bh); *beg = org; /* * Search again in current block * from beginning */ goto cont; } } bi->free_count -= (end - *beg); journal_mark_dirty(th, bh); brelse(bh); /* free block count calculation */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); PUT_SB_FREE_BLOCKS(s, SB_FREE_BLOCKS(s) - (end - *beg)); journal_mark_dirty(th, SB_BUFFER_WITH_SB(s)); return end - (*beg); } else { *beg = next; } } } static int bmap_hash_id(struct super_block *s, u32 id) { char *hash_in = NULL; unsigned long hash; unsigned bm; if (id <= 2) { bm = 1; } else { hash_in = (char *)(&id); hash = keyed_hash(hash_in, 4); bm = hash % reiserfs_bmap_count(s); if (!bm) bm = 1; } /* this can only be true when SB_BMAP_NR = 1 */ if (bm >= reiserfs_bmap_count(s)) bm = 0; return bm; } /* * hashes the id and then returns > 0 if the block group for the * corresponding hash is full */ static inline int block_group_used(struct super_block *s, u32 id) { int bm = bmap_hash_id(s, id); struct reiserfs_bitmap_info *info = &SB_AP_BITMAP(s)[bm]; /* * If we don't have cached information on this bitmap block, we're * going to have to load it later anyway. Loading it here allows us * to make a better decision. This favors long-term performance gain * with a better on-disk layout vs. a short term gain of skipping the * read and potentially having a bad placement. */ if (info->free_count == UINT_MAX) { struct buffer_head *bh = reiserfs_read_bitmap_block(s, bm); brelse(bh); } if (info->free_count > ((s->s_blocksize << 3) * 60 / 100)) { return 0; } return 1; } /* * the packing is returned in disk byte order */ __le32 reiserfs_choose_packing(struct inode * dir) { __le32 packing; if (TEST_OPTION(packing_groups, dir->i_sb)) { u32 parent_dir = le32_to_cpu(INODE_PKEY(dir)->k_dir_id); /* * some versions of reiserfsck expect packing locality 1 to be * special */ if (parent_dir == 1 || block_group_used(dir->i_sb, parent_dir)) packing = INODE_PKEY(dir)->k_objectid; else packing = INODE_PKEY(dir)->k_dir_id; } else packing = INODE_PKEY(dir)->k_objectid; return packing; } /* * Tries to find contiguous zero bit window (given size) in given region of * bitmap and place new blocks there. Returns number of allocated blocks. */ static int scan_bitmap(struct reiserfs_transaction_handle *th, b_blocknr_t * start, b_blocknr_t finish, int min, int max, int unfm, sector_t file_block) { int nr_allocated = 0; struct super_block *s = th->t_super; unsigned int bm, off; unsigned int end_bm, end_off; unsigned int off_max = s->s_blocksize << 3; BUG_ON(!th->t_trans_id); PROC_INFO_INC(s, scan_bitmap.call); /* No point in looking for more free blocks */ if (SB_FREE_BLOCKS(s) <= 0) return 0; get_bit_address(s, *start, &bm, &off); get_bit_address(s, finish, &end_bm, &end_off); if (bm > reiserfs_bmap_count(s)) return 0; if (end_bm > reiserfs_bmap_count(s)) end_bm = reiserfs_bmap_count(s); /* * When the bitmap is more than 10% free, anyone can allocate. * When it's less than 10% free, only files that already use the * bitmap are allowed. Once we pass 80% full, this restriction * is lifted. * * We do this so that files that grow later still have space close to * their original allocation. This improves locality, and presumably * performance as a result. * * This is only an allocation policy and does not make up for getting a * bad hint. Decent hinting must be implemented for this to work well. */ if (TEST_OPTION(skip_busy, s) && SB_FREE_BLOCKS(s) > SB_BLOCK_COUNT(s) / 20) { for (; bm < end_bm; bm++, off = 0) { if ((off && (!unfm || (file_block != 0))) || SB_AP_BITMAP(s)[bm].free_count > (s->s_blocksize << 3) / 10) nr_allocated = scan_bitmap_block(th, bm, &off, off_max, min, max, unfm); if (nr_allocated) goto ret; } /* we know from above that start is a reasonable number */ get_bit_address(s, *start, &bm, &off); } for (; bm < end_bm; bm++, off = 0) { nr_allocated = scan_bitmap_block(th, bm, &off, off_max, min, max, unfm); if (nr_allocated) goto ret; } nr_allocated = scan_bitmap_block(th, bm, &off, end_off + 1, min, max, unfm); ret: *start = bm * off_max + off; return nr_allocated; } static void _reiserfs_free_block(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t block, int for_unformatted) { struct super_block *s = th->t_super; struct reiserfs_super_block *rs; struct buffer_head *sbh, *bmbh; struct reiserfs_bitmap_info *apbi; unsigned int nr, offset; BUG_ON(!th->t_trans_id); PROC_INFO_INC(s, free_block); rs = SB_DISK_SUPER_BLOCK(s); sbh = SB_BUFFER_WITH_SB(s); apbi = SB_AP_BITMAP(s); get_bit_address(s, block, &nr, &offset); if (nr >= reiserfs_bmap_count(s)) { reiserfs_error(s, "vs-4075", "block %lu is out of range", block); return; } bmbh = reiserfs_read_bitmap_block(s, nr); if (!bmbh) return; reiserfs_prepare_for_journal(s, bmbh, 1); /* clear bit for the given block in bit map */ if (!reiserfs_test_and_clear_le_bit(offset, bmbh->b_data)) { reiserfs_error(s, "vs-4080", "block %lu: bit already cleared", block); } apbi[nr].free_count++; journal_mark_dirty(th, bmbh); brelse(bmbh); reiserfs_prepare_for_journal(s, sbh, 1); /* update super block */ set_sb_free_blocks(rs, sb_free_blocks(rs) + 1); journal_mark_dirty(th, sbh); if (for_unformatted) { int depth = reiserfs_write_unlock_nested(s); dquot_free_block_nodirty(inode, 1); reiserfs_write_lock_nested(s, depth); } } void reiserfs_free_block(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t block, int for_unformatted) { struct super_block *s = th->t_super; BUG_ON(!th->t_trans_id); RFALSE(!s, "vs-4061: trying to free block on nonexistent device"); if (!is_reusable(s, block, 1)) return; if (block > sb_block_count(REISERFS_SB(s)->s_rs)) { reiserfs_error(th->t_super, "bitmap-4072", "Trying to free block outside file system " "boundaries (%lu > %lu)", block, sb_block_count(REISERFS_SB(s)->s_rs)); return; } /* mark it before we clear it, just in case */ journal_mark_freed(th, s, block); _reiserfs_free_block(th, inode, block, for_unformatted); } /* preallocated blocks don't need to be run through journal_mark_freed */ static void reiserfs_free_prealloc_block(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t block) { BUG_ON(!th->t_trans_id); RFALSE(!th->t_super, "vs-4060: trying to free block on nonexistent device"); if (!is_reusable(th->t_super, block, 1)) return; _reiserfs_free_block(th, inode, block, 1); } static void __discard_prealloc(struct reiserfs_transaction_handle *th, struct reiserfs_inode_info *ei) { unsigned long save = ei->i_prealloc_block; int dirty = 0; struct inode *inode = &ei->vfs_inode; BUG_ON(!th->t_trans_id); #ifdef CONFIG_REISERFS_CHECK if (ei->i_prealloc_count < 0) reiserfs_error(th->t_super, "zam-4001", "inode has negative prealloc blocks count."); #endif while (ei->i_prealloc_count > 0) { b_blocknr_t block_to_free; /* * reiserfs_free_prealloc_block can drop the write lock, * which could allow another caller to free the same block. * We can protect against it by modifying the prealloc * state before calling it. */ block_to_free = ei->i_prealloc_block++; ei->i_prealloc_count--; reiserfs_free_prealloc_block(th, inode, block_to_free); dirty = 1; } if (dirty) reiserfs_update_sd(th, inode); ei->i_prealloc_block = save; list_del_init(&ei->i_prealloc_list); } /* FIXME: It should be inline function */ void reiserfs_discard_prealloc(struct reiserfs_transaction_handle *th, struct inode *inode) { struct reiserfs_inode_info *ei = REISERFS_I(inode); BUG_ON(!th->t_trans_id); if (ei->i_prealloc_count) __discard_prealloc(th, ei); } void reiserfs_discard_all_prealloc(struct reiserfs_transaction_handle *th) { struct list_head *plist = &SB_JOURNAL(th->t_super)->j_prealloc_list; BUG_ON(!th->t_trans_id); while (!list_empty(plist)) { struct reiserfs_inode_info *ei; ei = list_entry(plist->next, struct reiserfs_inode_info, i_prealloc_list); #ifdef CONFIG_REISERFS_CHECK if (!ei->i_prealloc_count) { reiserfs_error(th->t_super, "zam-4001", "inode is in prealloc list but has " "no preallocated blocks."); } #endif __discard_prealloc(th, ei); } } void reiserfs_init_alloc_options(struct super_block *s) { set_bit(_ALLOC_skip_busy, &SB_ALLOC_OPTS(s)); set_bit(_ALLOC_dirid_groups, &SB_ALLOC_OPTS(s)); set_bit(_ALLOC_packing_groups, &SB_ALLOC_OPTS(s)); } /* block allocator related options are parsed here */ int reiserfs_parse_alloc_options(struct super_block *s, char *options) { char *this_char, *value; /* clear default settings */ REISERFS_SB(s)->s_alloc_options.bits = 0; while ((this_char = strsep(&options, ":")) != NULL) { if ((value = strchr(this_char, '=')) != NULL) *value++ = 0; if (!strcmp(this_char, "concentrating_formatted_nodes")) { int temp; SET_OPTION(concentrating_formatted_nodes); temp = (value && *value) ? simple_strtoul(value, &value, 0) : 10; if (temp <= 0 || temp > 100) { REISERFS_SB(s)->s_alloc_options.border = 10; } else { REISERFS_SB(s)->s_alloc_options.border = 100 / temp; } continue; } if (!strcmp(this_char, "displacing_large_files")) { SET_OPTION(displacing_large_files); REISERFS_SB(s)->s_alloc_options.large_file_size = (value && *value) ? simple_strtoul(value, &value, 0) : 16; continue; } if (!strcmp(this_char, "displacing_new_packing_localities")) { SET_OPTION(displacing_new_packing_localities); continue; } if (!strcmp(this_char, "old_hashed_relocation")) { SET_OPTION(old_hashed_relocation); continue; } if (!strcmp(this_char, "new_hashed_relocation")) { SET_OPTION(new_hashed_relocation); continue; } if (!strcmp(this_char, "dirid_groups")) { SET_OPTION(dirid_groups); continue; } if (!strcmp(this_char, "oid_groups")) { SET_OPTION(oid_groups); continue; } if (!strcmp(this_char, "packing_groups")) { SET_OPTION(packing_groups); continue; } if (!strcmp(this_char, "hashed_formatted_nodes")) { SET_OPTION(hashed_formatted_nodes); continue; } if (!strcmp(this_char, "skip_busy")) { SET_OPTION(skip_busy); continue; } if (!strcmp(this_char, "hundredth_slices")) { SET_OPTION(hundredth_slices); continue; } if (!strcmp(this_char, "old_way")) { SET_OPTION(old_way); continue; } if (!strcmp(this_char, "displace_based_on_dirid")) { SET_OPTION(displace_based_on_dirid); continue; } if (!strcmp(this_char, "preallocmin")) { REISERFS_SB(s)->s_alloc_options.preallocmin = (value && *value) ? simple_strtoul(value, &value, 0) : 4; continue; } if (!strcmp(this_char, "preallocsize")) { REISERFS_SB(s)->s_alloc_options.preallocsize = (value && *value) ? simple_strtoul(value, &value, 0) : PREALLOCATION_SIZE; continue; } reiserfs_warning(s, "zam-4001", "unknown option - %s", this_char); return 1; } reiserfs_info(s, "allocator options = [%08x]\n", SB_ALLOC_OPTS(s)); return 0; } static void print_sep(struct seq_file *seq, int *first) { if (!*first) seq_puts(seq, ":"); else *first = 0; } void show_alloc_options(struct seq_file *seq, struct super_block *s) { int first = 1; if (SB_ALLOC_OPTS(s) == ((1 << _ALLOC_skip_busy) | (1 << _ALLOC_dirid_groups) | (1 << _ALLOC_packing_groups))) return; seq_puts(seq, ",alloc="); if (TEST_OPTION(concentrating_formatted_nodes, s)) { print_sep(seq, &first); if (REISERFS_SB(s)->s_alloc_options.border != 10) { seq_printf(seq, "concentrating_formatted_nodes=%d", 100 / REISERFS_SB(s)->s_alloc_options.border); } else seq_puts(seq, "concentrating_formatted_nodes"); } if (TEST_OPTION(displacing_large_files, s)) { print_sep(seq, &first); if (REISERFS_SB(s)->s_alloc_options.large_file_size != 16) { seq_printf(seq, "displacing_large_files=%lu", REISERFS_SB(s)->s_alloc_options.large_file_size); } else seq_puts(seq, "displacing_large_files"); } if (TEST_OPTION(displacing_new_packing_localities, s)) { print_sep(seq, &first); seq_puts(seq, "displacing_new_packing_localities"); } if (TEST_OPTION(old_hashed_relocation, s)) { print_sep(seq, &first); seq_puts(seq, "old_hashed_relocation"); } if (TEST_OPTION(new_hashed_relocation, s)) { print_sep(seq, &first); seq_puts(seq, "new_hashed_relocation"); } if (TEST_OPTION(dirid_groups, s)) { print_sep(seq, &first); seq_puts(seq, "dirid_groups"); } if (TEST_OPTION(oid_groups, s)) { print_sep(seq, &first); seq_puts(seq, "oid_groups"); } if (TEST_OPTION(packing_groups, s)) { print_sep(seq, &first); seq_puts(seq, "packing_groups"); } if (TEST_OPTION(hashed_formatted_nodes, s)) { print_sep(seq, &first); seq_puts(seq, "hashed_formatted_nodes"); } if (TEST_OPTION(skip_busy, s)) { print_sep(seq, &first); seq_puts(seq, "skip_busy"); } if (TEST_OPTION(hundredth_slices, s)) { print_sep(seq, &first); seq_puts(seq, "hundredth_slices"); } if (TEST_OPTION(old_way, s)) { print_sep(seq, &first); seq_puts(seq, "old_way"); } if (TEST_OPTION(displace_based_on_dirid, s)) { print_sep(seq, &first); seq_puts(seq, "displace_based_on_dirid"); } if (REISERFS_SB(s)->s_alloc_options.preallocmin != 0) { print_sep(seq, &first); seq_printf(seq, "preallocmin=%d", REISERFS_SB(s)->s_alloc_options.preallocmin); } if (REISERFS_SB(s)->s_alloc_options.preallocsize != 17) { print_sep(seq, &first); seq_printf(seq, "preallocsize=%d", REISERFS_SB(s)->s_alloc_options.preallocsize); } } static inline void new_hashed_relocation(reiserfs_blocknr_hint_t * hint) { char *hash_in; if (hint->formatted_node) { hash_in = (char *)&hint->key.k_dir_id; } else { if (!hint->inode) { /*hint->search_start = hint->beg;*/ hash_in = (char *)&hint->key.k_dir_id; } else if (TEST_OPTION(displace_based_on_dirid, hint->th->t_super)) hash_in = (char *)(&INODE_PKEY(hint->inode)->k_dir_id); else hash_in = (char *)(&INODE_PKEY(hint->inode)->k_objectid); } hint->search_start = hint->beg + keyed_hash(hash_in, 4) % (hint->end - hint->beg); } /* * Relocation based on dirid, hashing them into a given bitmap block * files. Formatted nodes are unaffected, a separate policy covers them */ static void dirid_groups(reiserfs_blocknr_hint_t * hint) { unsigned long hash; __u32 dirid = 0; int bm = 0; struct super_block *sb = hint->th->t_super; if (hint->inode) dirid = le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id); else if (hint->formatted_node) dirid = hint->key.k_dir_id; if (dirid) { bm = bmap_hash_id(sb, dirid); hash = bm * (sb->s_blocksize << 3); /* give a portion of the block group to metadata */ if (hint->inode) hash += sb->s_blocksize / 2; hint->search_start = hash; } } /* * Relocation based on oid, hashing them into a given bitmap block * files. Formatted nodes are unaffected, a separate policy covers them */ static void oid_groups(reiserfs_blocknr_hint_t * hint) { if (hint->inode) { unsigned long hash; __u32 oid; __u32 dirid; int bm; dirid = le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id); /* * keep the root dir and it's first set of subdirs close to * the start of the disk */ if (dirid <= 2) hash = (hint->inode->i_sb->s_blocksize << 3); else { oid = le32_to_cpu(INODE_PKEY(hint->inode)->k_objectid); bm = bmap_hash_id(hint->inode->i_sb, oid); hash = bm * (hint->inode->i_sb->s_blocksize << 3); } hint->search_start = hash; } } /* * returns 1 if it finds an indirect item and gets valid hint info * from it, otherwise 0 */ static int get_left_neighbor(reiserfs_blocknr_hint_t * hint) { struct treepath *path; struct buffer_head *bh; struct item_head *ih; int pos_in_item; __le32 *item; int ret = 0; /* * reiserfs code can call this function w/o pointer to path * structure supplied; then we rely on supplied search_start */ if (!hint->path) return 0; path = hint->path; bh = get_last_bh(path); RFALSE(!bh, "green-4002: Illegal path specified to get_left_neighbor"); ih = tp_item_head(path); pos_in_item = path->pos_in_item; item = tp_item_body(path); hint->search_start = bh->b_blocknr; /* * for indirect item: go to left and look for the first non-hole entry * in the indirect item */ if (!hint->formatted_node && is_indirect_le_ih(ih)) { if (pos_in_item == I_UNFM_NUM(ih)) pos_in_item--; while (pos_in_item >= 0) { int t = get_block_num(item, pos_in_item); if (t) { hint->search_start = t; ret = 1; break; } pos_in_item--; } } /* does result value fit into specified region? */ return ret; } /* * should be, if formatted node, then try to put on first part of the device * specified as number of percent with mount option device, else try to put * on last of device. This is not to say it is good code to do so, * but the effect should be measured. */ static inline void set_border_in_hint(struct super_block *s, reiserfs_blocknr_hint_t * hint) { b_blocknr_t border = SB_BLOCK_COUNT(s) / REISERFS_SB(s)->s_alloc_options.border; if (hint->formatted_node) hint->end = border - 1; else hint->beg = border; } static inline void displace_large_file(reiserfs_blocknr_hint_t * hint) { if (TEST_OPTION(displace_based_on_dirid, hint->th->t_super)) hint->search_start = hint->beg + keyed_hash((char *)(&INODE_PKEY(hint->inode)->k_dir_id), 4) % (hint->end - hint->beg); else hint->search_start = hint->beg + keyed_hash((char *)(&INODE_PKEY(hint->inode)->k_objectid), 4) % (hint->end - hint->beg); } static inline void hash_formatted_node(reiserfs_blocknr_hint_t * hint) { char *hash_in; if (!hint->inode) hash_in = (char *)&hint->key.k_dir_id; else if (TEST_OPTION(displace_based_on_dirid, hint->th->t_super)) hash_in = (char *)(&INODE_PKEY(hint->inode)->k_dir_id); else hash_in = (char *)(&INODE_PKEY(hint->inode)->k_objectid); hint->search_start = hint->beg + keyed_hash(hash_in, 4) % (hint->end - hint->beg); } static inline int this_blocknr_allocation_would_make_it_a_large_file(reiserfs_blocknr_hint_t * hint) { return hint->block == REISERFS_SB(hint->th->t_super)->s_alloc_options.large_file_size; } #ifdef DISPLACE_NEW_PACKING_LOCALITIES static inline void displace_new_packing_locality(reiserfs_blocknr_hint_t * hint) { struct in_core_key *key = &hint->key; hint->th->displace_new_blocks = 0; hint->search_start = hint->beg + keyed_hash((char *)(&key->k_objectid), 4) % (hint->end - hint->beg); } #endif static inline int old_hashed_relocation(reiserfs_blocknr_hint_t * hint) { b_blocknr_t border; u32 hash_in; if (hint->formatted_node || hint->inode == NULL) { return 0; } hash_in = le32_to_cpu((INODE_PKEY(hint->inode))->k_dir_id); border = hint->beg + (u32) keyed_hash(((char *)(&hash_in)), 4) % (hint->end - hint->beg - 1); if (border > hint->search_start) hint->search_start = border; return 1; } static inline int old_way(reiserfs_blocknr_hint_t * hint) { b_blocknr_t border; if (hint->formatted_node || hint->inode == NULL) { return 0; } border = hint->beg + le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id) % (hint->end - hint->beg); if (border > hint->search_start) hint->search_start = border; return 1; } static inline void hundredth_slices(reiserfs_blocknr_hint_t * hint) { struct in_core_key *key = &hint->key; b_blocknr_t slice_start; slice_start = (keyed_hash((char *)(&key->k_dir_id), 4) % 100) * (hint->end / 100); if (slice_start > hint->search_start || slice_start + (hint->end / 100) <= hint->search_start) { hint->search_start = slice_start; } } static void determine_search_start(reiserfs_blocknr_hint_t * hint, int amount_needed) { struct super_block *s = hint->th->t_super; int unfm_hint; hint->beg = 0; hint->end = SB_BLOCK_COUNT(s) - 1; /* This is former border algorithm. Now with tunable border offset */ if (concentrating_formatted_nodes(s)) set_border_in_hint(s, hint); #ifdef DISPLACE_NEW_PACKING_LOCALITIES /* * whenever we create a new directory, we displace it. At first * we will hash for location, later we might look for a moderately * empty place for it */ if (displacing_new_packing_localities(s) && hint->th->displace_new_blocks) { displace_new_packing_locality(hint); /* * we do not continue determine_search_start, * if new packing locality is being displaced */ return; } #endif /* * all persons should feel encouraged to add more special cases * here and test them */ if (displacing_large_files(s) && !hint->formatted_node && this_blocknr_allocation_would_make_it_a_large_file(hint)) { displace_large_file(hint); return; } /* * if none of our special cases is relevant, use the left * neighbor in the tree order of the new node we are allocating for */ if (hint->formatted_node && TEST_OPTION(hashed_formatted_nodes, s)) { hash_formatted_node(hint); return; } unfm_hint = get_left_neighbor(hint); /* * Mimic old block allocator behaviour, that is if VFS allowed for * preallocation, new blocks are displaced based on directory ID. * Also, if suggested search_start is less than last preallocated * block, we start searching from it, assuming that HDD dataflow * is faster in forward direction */ if (TEST_OPTION(old_way, s)) { if (!hint->formatted_node) { if (!reiserfs_hashed_relocation(s)) old_way(hint); else if (!reiserfs_no_unhashed_relocation(s)) old_hashed_relocation(hint); if (hint->inode && hint->search_start < REISERFS_I(hint->inode)->i_prealloc_block) hint->search_start = REISERFS_I(hint->inode)->i_prealloc_block; } return; } /* This is an approach proposed by Hans */ if (TEST_OPTION(hundredth_slices, s) && !(displacing_large_files(s) && !hint->formatted_node)) { hundredth_slices(hint); return; } /* old_hashed_relocation only works on unformatted */ if (!unfm_hint && !hint->formatted_node && TEST_OPTION(old_hashed_relocation, s)) { old_hashed_relocation(hint); } /* new_hashed_relocation works with both formatted/unformatted nodes */ if ((!unfm_hint || hint->formatted_node) && TEST_OPTION(new_hashed_relocation, s)) { new_hashed_relocation(hint); } /* dirid grouping works only on unformatted nodes */ if (!unfm_hint && !hint->formatted_node && TEST_OPTION(dirid_groups, s)) { dirid_groups(hint); } #ifdef DISPLACE_NEW_PACKING_LOCALITIES if (hint->formatted_node && TEST_OPTION(dirid_groups, s)) { dirid_groups(hint); } #endif /* oid grouping works only on unformatted nodes */ if (!unfm_hint && !hint->formatted_node && TEST_OPTION(oid_groups, s)) { oid_groups(hint); } return; } static int determine_prealloc_size(reiserfs_blocknr_hint_t * hint) { /* make minimum size a mount option and benchmark both ways */ /* we preallocate blocks only for regular files, specific size */ /* benchmark preallocating always and see what happens */ hint->prealloc_size = 0; if (!hint->formatted_node && hint->preallocate) { if (S_ISREG(hint->inode->i_mode) && !IS_PRIVATE(hint->inode) && hint->inode->i_size >= REISERFS_SB(hint->th->t_super)->s_alloc_options. preallocmin * hint->inode->i_sb->s_blocksize) hint->prealloc_size = REISERFS_SB(hint->th->t_super)->s_alloc_options. preallocsize - 1; } return CARRY_ON; } static inline int allocate_without_wrapping_disk(reiserfs_blocknr_hint_t * hint, b_blocknr_t * new_blocknrs, b_blocknr_t start, b_blocknr_t finish, int min, int amount_needed, int prealloc_size) { int rest = amount_needed; int nr_allocated; while (rest > 0 && start <= finish) { nr_allocated = scan_bitmap(hint->th, &start, finish, min, rest + prealloc_size, !hint->formatted_node, hint->block); if (nr_allocated == 0) /* no new blocks allocated, return */ break; /* fill free_blocknrs array first */ while (rest > 0 && nr_allocated > 0) { *new_blocknrs++ = start++; rest--; nr_allocated--; } /* do we have something to fill prealloc. array also ? */ if (nr_allocated > 0) { /* * it means prealloc_size was greater that 0 and * we do preallocation */ list_add(&REISERFS_I(hint->inode)->i_prealloc_list, &SB_JOURNAL(hint->th->t_super)-> j_prealloc_list); REISERFS_I(hint->inode)->i_prealloc_block = start; REISERFS_I(hint->inode)->i_prealloc_count = nr_allocated; break; } } return (amount_needed - rest); } static inline int blocknrs_and_prealloc_arrays_from_search_start (reiserfs_blocknr_hint_t * hint, b_blocknr_t * new_blocknrs, int amount_needed) { struct super_block *s = hint->th->t_super; b_blocknr_t start = hint->search_start; b_blocknr_t finish = SB_BLOCK_COUNT(s) - 1; int passno = 0; int nr_allocated = 0; int depth; determine_prealloc_size(hint); if (!hint->formatted_node) { int quota_ret; #ifdef REISERQUOTA_DEBUG reiserfs_debug(s, REISERFS_DEBUG_CODE, "reiserquota: allocating %d blocks id=%u", amount_needed, hint->inode->i_uid); #endif depth = reiserfs_write_unlock_nested(s); quota_ret = dquot_alloc_block_nodirty(hint->inode, amount_needed); if (quota_ret) { /* Quota exceeded? */ reiserfs_write_lock_nested(s, depth); return QUOTA_EXCEEDED; } if (hint->preallocate && hint->prealloc_size) { #ifdef REISERQUOTA_DEBUG reiserfs_debug(s, REISERFS_DEBUG_CODE, "reiserquota: allocating (prealloc) %d blocks id=%u", hint->prealloc_size, hint->inode->i_uid); #endif quota_ret = dquot_prealloc_block_nodirty(hint->inode, hint->prealloc_size); if (quota_ret) hint->preallocate = hint->prealloc_size = 0; } /* for unformatted nodes, force large allocations */ reiserfs_write_lock_nested(s, depth); } do { switch (passno++) { case 0: /* Search from hint->search_start to end of disk */ start = hint->search_start; finish = SB_BLOCK_COUNT(s) - 1; break; case 1: /* Search from hint->beg to hint->search_start */ start = hint->beg; finish = hint->search_start; break; case 2: /* Last chance: Search from 0 to hint->beg */ start = 0; finish = hint->beg; break; default: /* We've tried searching everywhere, not enough space */ /* Free the blocks */ if (!hint->formatted_node) { #ifdef REISERQUOTA_DEBUG reiserfs_debug(s, REISERFS_DEBUG_CODE, "reiserquota: freeing (nospace) %d blocks id=%u", amount_needed + hint->prealloc_size - nr_allocated, hint->inode->i_uid); #endif /* Free not allocated blocks */ depth = reiserfs_write_unlock_nested(s); dquot_free_block_nodirty(hint->inode, amount_needed + hint->prealloc_size - nr_allocated); reiserfs_write_lock_nested(s, depth); } while (nr_allocated--) reiserfs_free_block(hint->th, hint->inode, new_blocknrs[nr_allocated], !hint->formatted_node); return NO_DISK_SPACE; } } while ((nr_allocated += allocate_without_wrapping_disk(hint, new_blocknrs + nr_allocated, start, finish, 1, amount_needed - nr_allocated, hint-> prealloc_size)) < amount_needed); if (!hint->formatted_node && amount_needed + hint->prealloc_size > nr_allocated + REISERFS_I(hint->inode)->i_prealloc_count) { /* Some of preallocation blocks were not allocated */ #ifdef REISERQUOTA_DEBUG reiserfs_debug(s, REISERFS_DEBUG_CODE, "reiserquota: freeing (failed prealloc) %d blocks id=%u", amount_needed + hint->prealloc_size - nr_allocated - REISERFS_I(hint->inode)->i_prealloc_count, hint->inode->i_uid); #endif depth = reiserfs_write_unlock_nested(s); dquot_free_block_nodirty(hint->inode, amount_needed + hint->prealloc_size - nr_allocated - REISERFS_I(hint->inode)-> i_prealloc_count); reiserfs_write_lock_nested(s, depth); } return CARRY_ON; } /* grab new blocknrs from preallocated list */ /* return amount still needed after using them */ static int use_preallocated_list_if_available(reiserfs_blocknr_hint_t * hint, b_blocknr_t * new_blocknrs, int amount_needed) { struct inode *inode = hint->inode; if (REISERFS_I(inode)->i_prealloc_count > 0) { while (amount_needed) { *new_blocknrs++ = REISERFS_I(inode)->i_prealloc_block++; REISERFS_I(inode)->i_prealloc_count--; amount_needed--; if (REISERFS_I(inode)->i_prealloc_count <= 0) { list_del(&REISERFS_I(inode)->i_prealloc_list); break; } } } /* return amount still needed after using preallocated blocks */ return amount_needed; } int reiserfs_allocate_blocknrs(reiserfs_blocknr_hint_t *hint, b_blocknr_t *new_blocknrs, int amount_needed, /* Amount of blocks we have already reserved */ int reserved_by_us) { int initial_amount_needed = amount_needed; int ret; struct super_block *s = hint->th->t_super; /* Check if there is enough space, taking into account reserved space */ if (SB_FREE_BLOCKS(s) - REISERFS_SB(s)->reserved_blocks < amount_needed - reserved_by_us) return NO_DISK_SPACE; /* should this be if !hint->inode && hint->preallocate? */ /* do you mean hint->formatted_node can be removed ? - Zam */ /* * hint->formatted_node cannot be removed because we try to access * inode information here, and there is often no inode associated with * metadata allocations - green */ if (!hint->formatted_node && hint->preallocate) { amount_needed = use_preallocated_list_if_available (hint, new_blocknrs, amount_needed); /* * We have all the block numbers we need from the * prealloc list */ if (amount_needed == 0) return CARRY_ON; new_blocknrs += (initial_amount_needed - amount_needed); } /* find search start and save it in hint structure */ determine_search_start(hint, amount_needed); if (hint->search_start >= SB_BLOCK_COUNT(s)) hint->search_start = SB_BLOCK_COUNT(s) - 1; /* allocation itself; fill new_blocknrs and preallocation arrays */ ret = blocknrs_and_prealloc_arrays_from_search_start (hint, new_blocknrs, amount_needed); /* * We used prealloc. list to fill (partially) new_blocknrs array. * If final allocation fails we need to return blocks back to * prealloc. list or just free them. -- Zam (I chose second * variant) */ if (ret != CARRY_ON) { while (amount_needed++ < initial_amount_needed) { reiserfs_free_block(hint->th, hint->inode, *(--new_blocknrs), 1); } } return ret; } void reiserfs_cache_bitmap_metadata(struct super_block *sb, struct buffer_head *bh, struct reiserfs_bitmap_info *info) { unsigned long *cur = (unsigned long *)(bh->b_data + bh->b_size); /* The first bit must ALWAYS be 1 */ if (!reiserfs_test_le_bit(0, (unsigned long *)bh->b_data)) reiserfs_error(sb, "reiserfs-2025", "bitmap block %lu is " "corrupted: first bit must be 1", bh->b_blocknr); info->free_count = 0; while (--cur >= (unsigned long *)bh->b_data) { /* 0 and ~0 are special, we can optimize for them */ if (*cur == 0) info->free_count += BITS_PER_LONG; else if (*cur != ~0L) /* A mix, investigate */ info->free_count += BITS_PER_LONG - hweight_long(*cur); } } struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, unsigned int bitmap) { b_blocknr_t block = (sb->s_blocksize << 3) * bitmap; struct reiserfs_bitmap_info *info = SB_AP_BITMAP(sb) + bitmap; struct buffer_head *bh; /* * Way old format filesystems had the bitmaps packed up front. * I doubt there are any of these left, but just in case... */ if (unlikely(test_bit(REISERFS_OLD_FORMAT, &REISERFS_SB(sb)->s_properties))) block = REISERFS_SB(sb)->s_sbh->b_blocknr + 1 + bitmap; else if (bitmap == 0) block = (REISERFS_DISK_OFFSET_IN_BYTES >> sb->s_blocksize_bits) + 1; bh = sb_bread(sb, block); if (bh == NULL) reiserfs_warning(sb, "sh-2029: %s: bitmap block (#%u) " "reading failed", __func__, block); else { if (buffer_locked(bh)) { int depth; PROC_INFO_INC(sb, scan_bitmap.wait); depth = reiserfs_write_unlock_nested(sb); __wait_on_buffer(bh); reiserfs_write_lock_nested(sb, depth); } BUG_ON(!buffer_uptodate(bh)); BUG_ON(atomic_read(&bh->b_count) == 0); if (info->free_count == UINT_MAX) reiserfs_cache_bitmap_metadata(sb, bh, info); } return bh; } int reiserfs_init_bitmap_cache(struct super_block *sb) { struct reiserfs_bitmap_info *bitmap; unsigned int bmap_nr = reiserfs_bmap_count(sb); bitmap = vmalloc(array_size(bmap_nr, sizeof(*bitmap))); if (bitmap == NULL) return -ENOMEM; memset(bitmap, 0xff, sizeof(*bitmap) * bmap_nr); SB_AP_BITMAP(sb) = bitmap; return 0; } void reiserfs_free_bitmap_cache(struct super_block *sb) { if (SB_AP_BITMAP(sb)) { vfree(SB_AP_BITMAP(sb)); SB_AP_BITMAP(sb) = NULL; } } |
| 11 6 1 6 6 10 10 10 11 11 10 10 10 10 10 12 8 10 132 132 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc. * Copyright (c) 2008 Dave Chinner * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_trace.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_log.h" #include "xfs_log_priv.h" #ifdef DEBUG /* * Check that the list is sorted as it should be. * * Called with the ail lock held, but we don't want to assert fail with it * held otherwise we'll lock everything up and won't be able to debug the * cause. Hence we sample and check the state under the AIL lock and return if * everything is fine, otherwise we drop the lock and run the ASSERT checks. * Asserts may not be fatal, so pick the lock back up and continue onwards. */ STATIC void xfs_ail_check( struct xfs_ail *ailp, struct xfs_log_item *lip) __must_hold(&ailp->ail_lock) { struct xfs_log_item *prev_lip; struct xfs_log_item *next_lip; xfs_lsn_t prev_lsn = NULLCOMMITLSN; xfs_lsn_t next_lsn = NULLCOMMITLSN; xfs_lsn_t lsn; bool in_ail; if (list_empty(&ailp->ail_head)) return; /* * Sample then check the next and previous entries are valid. */ in_ail = test_bit(XFS_LI_IN_AIL, &lip->li_flags); prev_lip = list_entry(lip->li_ail.prev, struct xfs_log_item, li_ail); if (&prev_lip->li_ail != &ailp->ail_head) prev_lsn = prev_lip->li_lsn; next_lip = list_entry(lip->li_ail.next, struct xfs_log_item, li_ail); if (&next_lip->li_ail != &ailp->ail_head) next_lsn = next_lip->li_lsn; lsn = lip->li_lsn; if (in_ail && (prev_lsn == NULLCOMMITLSN || XFS_LSN_CMP(prev_lsn, lsn) <= 0) && (next_lsn == NULLCOMMITLSN || XFS_LSN_CMP(next_lsn, lsn) >= 0)) return; spin_unlock(&ailp->ail_lock); ASSERT(in_ail); ASSERT(prev_lsn == NULLCOMMITLSN || XFS_LSN_CMP(prev_lsn, lsn) <= 0); ASSERT(next_lsn == NULLCOMMITLSN || XFS_LSN_CMP(next_lsn, lsn) >= 0); spin_lock(&ailp->ail_lock); } #else /* !DEBUG */ #define xfs_ail_check(a,l) #endif /* DEBUG */ /* * Return a pointer to the last item in the AIL. If the AIL is empty, then * return NULL. */ static struct xfs_log_item * xfs_ail_max( struct xfs_ail *ailp) { if (list_empty(&ailp->ail_head)) return NULL; return list_entry(ailp->ail_head.prev, struct xfs_log_item, li_ail); } /* * Return a pointer to the item which follows the given item in the AIL. If * the given item is the last item in the list, then return NULL. */ static struct xfs_log_item * xfs_ail_next( struct xfs_ail *ailp, struct xfs_log_item *lip) { if (lip->li_ail.next == &ailp->ail_head) return NULL; return list_first_entry(&lip->li_ail, struct xfs_log_item, li_ail); } /* * This is called by the log manager code to determine the LSN of the tail of * the log. This is exactly the LSN of the first item in the AIL. If the AIL * is empty, then this function returns 0. * * We need the AIL lock in order to get a coherent read of the lsn of the last * item in the AIL. */ static xfs_lsn_t __xfs_ail_min_lsn( struct xfs_ail *ailp) { struct xfs_log_item *lip = xfs_ail_min(ailp); if (lip) return lip->li_lsn; return 0; } xfs_lsn_t xfs_ail_min_lsn( struct xfs_ail *ailp) { xfs_lsn_t lsn; spin_lock(&ailp->ail_lock); lsn = __xfs_ail_min_lsn(ailp); spin_unlock(&ailp->ail_lock); return lsn; } /* * The cursor keeps track of where our current traversal is up to by tracking * the next item in the list for us. However, for this to be safe, removing an * object from the AIL needs to invalidate any cursor that points to it. hence * the traversal cursor needs to be linked to the struct xfs_ail so that * deletion can search all the active cursors for invalidation. */ STATIC void xfs_trans_ail_cursor_init( struct xfs_ail *ailp, struct xfs_ail_cursor *cur) { cur->item = NULL; list_add_tail(&cur->list, &ailp->ail_cursors); } /* * Get the next item in the traversal and advance the cursor. If the cursor * was invalidated (indicated by a lip of 1), restart the traversal. */ struct xfs_log_item * xfs_trans_ail_cursor_next( struct xfs_ail *ailp, struct xfs_ail_cursor *cur) { struct xfs_log_item *lip = cur->item; if ((uintptr_t)lip & 1) lip = xfs_ail_min(ailp); if (lip) cur->item = xfs_ail_next(ailp, lip); return lip; } /* * When the traversal is complete, we need to remove the cursor from the list * of traversing cursors. */ void xfs_trans_ail_cursor_done( struct xfs_ail_cursor *cur) { cur->item = NULL; list_del_init(&cur->list); } /* * Invalidate any cursor that is pointing to this item. This is called when an * item is removed from the AIL. Any cursor pointing to this object is now * invalid and the traversal needs to be terminated so it doesn't reference a * freed object. We set the low bit of the cursor item pointer so we can * distinguish between an invalidation and the end of the list when getting the * next item from the cursor. */ STATIC void xfs_trans_ail_cursor_clear( struct xfs_ail *ailp, struct xfs_log_item *lip) { struct xfs_ail_cursor *cur; list_for_each_entry(cur, &ailp->ail_cursors, list) { if (cur->item == lip) cur->item = (struct xfs_log_item *) ((uintptr_t)cur->item | 1); } } /* * Find the first item in the AIL with the given @lsn by searching in ascending * LSN order and initialise the cursor to point to the next item for a * ascending traversal. Pass a @lsn of zero to initialise the cursor to the * first item in the AIL. Returns NULL if the list is empty. */ struct xfs_log_item * xfs_trans_ail_cursor_first( struct xfs_ail *ailp, struct xfs_ail_cursor *cur, xfs_lsn_t lsn) { struct xfs_log_item *lip; xfs_trans_ail_cursor_init(ailp, cur); if (lsn == 0) { lip = xfs_ail_min(ailp); goto out; } list_for_each_entry(lip, &ailp->ail_head, li_ail) { if (XFS_LSN_CMP(lip->li_lsn, lsn) >= 0) goto out; } return NULL; out: if (lip) cur->item = xfs_ail_next(ailp, lip); return lip; } static struct xfs_log_item * __xfs_trans_ail_cursor_last( struct xfs_ail *ailp, xfs_lsn_t lsn) { struct xfs_log_item *lip; list_for_each_entry_reverse(lip, &ailp->ail_head, li_ail) { if (XFS_LSN_CMP(lip->li_lsn, lsn) <= 0) return lip; } return NULL; } /* * Find the last item in the AIL with the given @lsn by searching in descending * LSN order and initialise the cursor to point to that item. If there is no * item with the value of @lsn, then it sets the cursor to the last item with an * LSN lower than @lsn. Returns NULL if the list is empty. */ struct xfs_log_item * xfs_trans_ail_cursor_last( struct xfs_ail *ailp, struct xfs_ail_cursor *cur, xfs_lsn_t lsn) { xfs_trans_ail_cursor_init(ailp, cur); cur->item = __xfs_trans_ail_cursor_last(ailp, lsn); return cur->item; } /* * Splice the log item list into the AIL at the given LSN. We splice to the * tail of the given LSN to maintain insert order for push traversals. The * cursor is optional, allowing repeated updates to the same LSN to avoid * repeated traversals. This should not be called with an empty list. */ static void xfs_ail_splice( struct xfs_ail *ailp, struct xfs_ail_cursor *cur, struct list_head *list, xfs_lsn_t lsn) { struct xfs_log_item *lip; ASSERT(!list_empty(list)); /* * Use the cursor to determine the insertion point if one is * provided. If not, or if the one we got is not valid, * find the place in the AIL where the items belong. */ lip = cur ? cur->item : NULL; if (!lip || (uintptr_t)lip & 1) lip = __xfs_trans_ail_cursor_last(ailp, lsn); /* * If a cursor is provided, we know we're processing the AIL * in lsn order, and future items to be spliced in will * follow the last one being inserted now. Update the * cursor to point to that last item, now while we have a * reliable pointer to it. */ if (cur) cur->item = list_entry(list->prev, struct xfs_log_item, li_ail); /* * Finally perform the splice. Unless the AIL was empty, * lip points to the item in the AIL _after_ which the new * items should go. If lip is null the AIL was empty, so * the new items go at the head of the AIL. */ if (lip) list_splice(list, &lip->li_ail); else list_splice(list, &ailp->ail_head); } /* * Delete the given item from the AIL. Return a pointer to the item. */ static void xfs_ail_delete( struct xfs_ail *ailp, struct xfs_log_item *lip) { xfs_ail_check(ailp, lip); list_del(&lip->li_ail); xfs_trans_ail_cursor_clear(ailp, lip); } /* * Requeue a failed buffer for writeback. * * We clear the log item failed state here as well, but we have to be careful * about reference counts because the only active reference counts on the buffer * may be the failed log items. Hence if we clear the log item failed state * before queuing the buffer for IO we can release all active references to * the buffer and free it, leading to use after free problems in * xfs_buf_delwri_queue. It makes no difference to the buffer or log items which * order we process them in - the buffer is locked, and we own the buffer list * so nothing on them is going to change while we are performing this action. * * Hence we can safely queue the buffer for IO before we clear the failed log * item state, therefore always having an active reference to the buffer and * avoiding the transient zero-reference state that leads to use-after-free. */ static inline int xfsaild_resubmit_item( struct xfs_log_item *lip, struct list_head *buffer_list) { struct xfs_buf *bp = lip->li_buf; if (!xfs_buf_trylock(bp)) return XFS_ITEM_LOCKED; if (!xfs_buf_delwri_queue(bp, buffer_list)) { xfs_buf_unlock(bp); return XFS_ITEM_FLUSHING; } /* protected by ail_lock */ list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { if (bp->b_flags & _XBF_INODES) clear_bit(XFS_LI_FAILED, &lip->li_flags); else xfs_clear_li_failed(lip); } xfs_buf_unlock(bp); return XFS_ITEM_SUCCESS; } static inline uint xfsaild_push_item( struct xfs_ail *ailp, struct xfs_log_item *lip) { /* * If log item pinning is enabled, skip the push and track the item as * pinned. This can help induce head-behind-tail conditions. */ if (XFS_TEST_ERROR(false, ailp->ail_log->l_mp, XFS_ERRTAG_LOG_ITEM_PIN)) return XFS_ITEM_PINNED; /* * Consider the item pinned if a push callback is not defined so the * caller will force the log. This should only happen for intent items * as they are unpinned once the associated done item is committed to * the on-disk log. */ if (!lip->li_ops->iop_push) return XFS_ITEM_PINNED; if (test_bit(XFS_LI_FAILED, &lip->li_flags)) return xfsaild_resubmit_item(lip, &ailp->ail_buf_list); return lip->li_ops->iop_push(lip, &ailp->ail_buf_list); } /* * Compute the LSN that we'd need to push the log tail towards in order to have * at least 25% of the log space free. If the log free space already meets this * threshold, this function returns the lowest LSN in the AIL to slowly keep * writeback ticking over and the tail of the log moving forward. */ static xfs_lsn_t xfs_ail_calc_push_target( struct xfs_ail *ailp) { struct xlog *log = ailp->ail_log; struct xfs_log_item *lip; xfs_lsn_t target_lsn; xfs_lsn_t max_lsn; xfs_lsn_t min_lsn; int32_t free_bytes; uint32_t target_block; uint32_t target_cycle; lockdep_assert_held(&ailp->ail_lock); lip = xfs_ail_max(ailp); if (!lip) return NULLCOMMITLSN; max_lsn = lip->li_lsn; min_lsn = __xfs_ail_min_lsn(ailp); /* * If we are supposed to push all the items in the AIL, we want to push * to the current head. We then clear the push flag so that we don't * keep pushing newly queued items beyond where the push all command was * run. If the push waiter wants to empty the ail, it should queue * itself on the ail_empty wait queue. */ if (test_and_clear_bit(XFS_AIL_OPSTATE_PUSH_ALL, &ailp->ail_opstate)) return max_lsn; /* If someone wants the AIL empty, keep pushing everything we have. */ if (waitqueue_active(&ailp->ail_empty)) return max_lsn; /* * Background pushing - attempt to keep 25% of the log free and if we * have that much free retain the existing target. */ free_bytes = log->l_logsize - xlog_lsn_sub(log, max_lsn, min_lsn); if (free_bytes >= log->l_logsize >> 2) return ailp->ail_target; target_cycle = CYCLE_LSN(min_lsn); target_block = BLOCK_LSN(min_lsn) + (log->l_logBBsize >> 2); if (target_block >= log->l_logBBsize) { target_block -= log->l_logBBsize; target_cycle += 1; } target_lsn = xlog_assign_lsn(target_cycle, target_block); /* Cap the target to the highest LSN known to be in the AIL. */ if (XFS_LSN_CMP(target_lsn, max_lsn) > 0) return max_lsn; /* If the existing target is higher than the new target, keep it. */ if (XFS_LSN_CMP(ailp->ail_target, target_lsn) >= 0) return ailp->ail_target; return target_lsn; } static long xfsaild_push( struct xfs_ail *ailp) { struct xfs_mount *mp = ailp->ail_log->l_mp; struct xfs_ail_cursor cur; struct xfs_log_item *lip; xfs_lsn_t lsn; long tout; int stuck = 0; int flushing = 0; int count = 0; /* * If we encountered pinned items or did not finish writing out all * buffers the last time we ran, force a background CIL push to get the * items unpinned in the near future. We do not wait on the CIL push as * that could stall us for seconds if there is enough background IO * load. Stalling for that long when the tail of the log is pinned and * needs flushing will hard stop the transaction subsystem when log * space runs out. */ if (ailp->ail_log_flush && ailp->ail_last_pushed_lsn == 0 && (!list_empty_careful(&ailp->ail_buf_list) || xfs_ail_min_lsn(ailp))) { ailp->ail_log_flush = 0; XFS_STATS_INC(mp, xs_push_ail_flush); xlog_cil_flush(ailp->ail_log); } spin_lock(&ailp->ail_lock); WRITE_ONCE(ailp->ail_target, xfs_ail_calc_push_target(ailp)); if (ailp->ail_target == NULLCOMMITLSN) goto out_done; /* we're done if the AIL is empty or our push has reached the end */ lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->ail_last_pushed_lsn); if (!lip) goto out_done_cursor; XFS_STATS_INC(mp, xs_push_ail); ASSERT(ailp->ail_target != NULLCOMMITLSN); lsn = lip->li_lsn; while ((XFS_LSN_CMP(lip->li_lsn, ailp->ail_target) <= 0)) { int lock_result; if (test_bit(XFS_LI_FLUSHING, &lip->li_flags)) goto next_item; /* * Note that iop_push may unlock and reacquire the AIL lock. We * rely on the AIL cursor implementation to be able to deal with * the dropped lock. */ lock_result = xfsaild_push_item(ailp, lip); switch (lock_result) { case XFS_ITEM_SUCCESS: XFS_STATS_INC(mp, xs_push_ail_success); trace_xfs_ail_push(lip); ailp->ail_last_pushed_lsn = lsn; break; case XFS_ITEM_FLUSHING: /* * The item or its backing buffer is already being * flushed. The typical reason for that is that an * inode buffer is locked because we already pushed the * updates to it as part of inode clustering. * * We do not want to stop flushing just because lots * of items are already being flushed, but we need to * re-try the flushing relatively soon if most of the * AIL is being flushed. */ XFS_STATS_INC(mp, xs_push_ail_flushing); trace_xfs_ail_flushing(lip); flushing++; ailp->ail_last_pushed_lsn = lsn; break; case XFS_ITEM_PINNED: XFS_STATS_INC(mp, xs_push_ail_pinned); trace_xfs_ail_pinned(lip); stuck++; ailp->ail_log_flush++; break; case XFS_ITEM_LOCKED: XFS_STATS_INC(mp, xs_push_ail_locked); trace_xfs_ail_locked(lip); stuck++; break; default: ASSERT(0); break; } count++; /* * Are there too many items we can't do anything with? * * If we are skipping too many items because we can't flush * them or they are already being flushed, we back off and * given them time to complete whatever operation is being * done. i.e. remove pressure from the AIL while we can't make * progress so traversals don't slow down further inserts and * removals to/from the AIL. * * The value of 100 is an arbitrary magic number based on * observation. */ if (stuck > 100) break; next_item: lip = xfs_trans_ail_cursor_next(ailp, &cur); if (lip == NULL) break; if (lip->li_lsn != lsn && count > 1000) break; lsn = lip->li_lsn; } out_done_cursor: xfs_trans_ail_cursor_done(&cur); out_done: spin_unlock(&ailp->ail_lock); if (xfs_buf_delwri_submit_nowait(&ailp->ail_buf_list)) ailp->ail_log_flush++; if (!count || XFS_LSN_CMP(lsn, ailp->ail_target) >= 0) { /* * We reached the target or the AIL is empty, so wait a bit * longer for I/O to complete and remove pushed items from the * AIL before we start the next scan from the start of the AIL. */ tout = 50; ailp->ail_last_pushed_lsn = 0; } else if (((stuck + flushing) * 100) / count > 90) { /* * Either there is a lot of contention on the AIL or we are * stuck due to operations in progress. "Stuck" in this case * is defined as >90% of the items we tried to push were stuck. * * Backoff a bit more to allow some I/O to complete before * restarting from the start of the AIL. This prevents us from * spinning on the same items, and if they are pinned will all * the restart to issue a log force to unpin the stuck items. */ tout = 20; ailp->ail_last_pushed_lsn = 0; } else { /* * Assume we have more work to do in a short while. */ tout = 0; } return tout; } static int xfsaild( void *data) { struct xfs_ail *ailp = data; long tout = 0; /* milliseconds */ unsigned int noreclaim_flag; noreclaim_flag = memalloc_noreclaim_save(); set_freezable(); while (1) { if (tout) set_current_state(TASK_KILLABLE|TASK_FREEZABLE); else set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); /* * Check kthread_should_stop() after we set the task state to * guarantee that we either see the stop bit and exit or the * task state is reset to runnable such that it's not scheduled * out indefinitely and detects the stop bit at next iteration. * A memory barrier is included in above task state set to * serialize again kthread_stop(). */ if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); /* * The caller forces out the AIL before stopping the * thread in the common case, which means the delwri * queue is drained. In the shutdown case, the queue may * still hold relogged buffers that haven't been * submitted because they were pinned since added to the * queue. * * Log I/O error processing stales the underlying buffer * and clears the delwri state, expecting the buf to be * removed on the next submission attempt. That won't * happen if we're shutting down, so this is the last * opportunity to release such buffers from the queue. */ ASSERT(list_empty(&ailp->ail_buf_list) || xlog_is_shutdown(ailp->ail_log)); xfs_buf_delwri_cancel(&ailp->ail_buf_list); break; } /* Idle if the AIL is empty. */ spin_lock(&ailp->ail_lock); if (!xfs_ail_min(ailp) && list_empty(&ailp->ail_buf_list)) { spin_unlock(&ailp->ail_lock); schedule(); tout = 0; continue; } spin_unlock(&ailp->ail_lock); if (tout) schedule_timeout(msecs_to_jiffies(tout)); __set_current_state(TASK_RUNNING); try_to_freeze(); tout = xfsaild_push(ailp); } memalloc_noreclaim_restore(noreclaim_flag); return 0; } /* * Push out all items in the AIL immediately and wait until the AIL is empty. */ void xfs_ail_push_all_sync( struct xfs_ail *ailp) { DEFINE_WAIT(wait); spin_lock(&ailp->ail_lock); while (xfs_ail_max(ailp) != NULL) { prepare_to_wait(&ailp->ail_empty, &wait, TASK_UNINTERRUPTIBLE); wake_up_process(ailp->ail_task); spin_unlock(&ailp->ail_lock); schedule(); spin_lock(&ailp->ail_lock); } spin_unlock(&ailp->ail_lock); finish_wait(&ailp->ail_empty, &wait); } void __xfs_ail_assign_tail_lsn( struct xfs_ail *ailp) { struct xlog *log = ailp->ail_log; xfs_lsn_t tail_lsn; assert_spin_locked(&ailp->ail_lock); if (xlog_is_shutdown(log)) return; tail_lsn = __xfs_ail_min_lsn(ailp); if (!tail_lsn) tail_lsn = ailp->ail_head_lsn; WRITE_ONCE(log->l_tail_space, xlog_lsn_sub(log, ailp->ail_head_lsn, tail_lsn)); trace_xfs_log_assign_tail_lsn(log, tail_lsn); atomic64_set(&log->l_tail_lsn, tail_lsn); } /* * Callers should pass the original tail lsn so that we can detect if the tail * has moved as a result of the operation that was performed. If the caller * needs to force a tail space update, it should pass NULLCOMMITLSN to bypass * the "did the tail LSN change?" checks. If the caller wants to avoid a tail * update (e.g. it knows the tail did not change) it should pass an @old_lsn of * 0. */ void xfs_ail_update_finish( struct xfs_ail *ailp, xfs_lsn_t old_lsn) __releases(ailp->ail_lock) { struct xlog *log = ailp->ail_log; /* If the tail lsn hasn't changed, don't do updates or wakeups. */ if (!old_lsn || old_lsn == __xfs_ail_min_lsn(ailp)) { spin_unlock(&ailp->ail_lock); return; } __xfs_ail_assign_tail_lsn(ailp); if (list_empty(&ailp->ail_head)) wake_up_all(&ailp->ail_empty); spin_unlock(&ailp->ail_lock); xfs_log_space_wake(log->l_mp); } /* * xfs_trans_ail_update - bulk AIL insertion operation. * * @xfs_trans_ail_update takes an array of log items that all need to be * positioned at the same LSN in the AIL. If an item is not in the AIL, it will * be added. Otherwise, it will be repositioned by removing it and re-adding * it to the AIL. If we move the first item in the AIL, update the log tail to * match the new minimum LSN in the AIL. * * This function takes the AIL lock once to execute the update operations on * all the items in the array, and as such should not be called with the AIL * lock held. As a result, once we have the AIL lock, we need to check each log * item LSN to confirm it needs to be moved forward in the AIL. * * To optimise the insert operation, we delete all the items from the AIL in * the first pass, moving them into a temporary list, then splice the temporary * list into the correct position in the AIL. This avoids needing to do an * insert operation on every item. * * This function must be called with the AIL lock held. The lock is dropped * before returning. */ void xfs_trans_ail_update_bulk( struct xfs_ail *ailp, struct xfs_ail_cursor *cur, struct xfs_log_item **log_items, int nr_items, xfs_lsn_t lsn) __releases(ailp->ail_lock) { struct xfs_log_item *mlip; xfs_lsn_t tail_lsn = 0; int i; LIST_HEAD(tmp); ASSERT(nr_items > 0); /* Not required, but true. */ mlip = xfs_ail_min(ailp); for (i = 0; i < nr_items; i++) { struct xfs_log_item *lip = log_items[i]; if (test_and_set_bit(XFS_LI_IN_AIL, &lip->li_flags)) { /* check if we really need to move the item */ if (XFS_LSN_CMP(lsn, lip->li_lsn) <= 0) continue; trace_xfs_ail_move(lip, lip->li_lsn, lsn); if (mlip == lip && !tail_lsn) tail_lsn = lip->li_lsn; xfs_ail_delete(ailp, lip); } else { trace_xfs_ail_insert(lip, 0, lsn); } lip->li_lsn = lsn; list_add_tail(&lip->li_ail, &tmp); } if (!list_empty(&tmp)) xfs_ail_splice(ailp, cur, &tmp, lsn); /* * If this is the first insert, wake up the push daemon so it can * actively scan for items to push. We also need to do a log tail * LSN update to ensure that it is correctly tracked by the log, so * set the tail_lsn to NULLCOMMITLSN so that xfs_ail_update_finish() * will see that the tail lsn has changed and will update the tail * appropriately. */ if (!mlip) { wake_up_process(ailp->ail_task); tail_lsn = NULLCOMMITLSN; } xfs_ail_update_finish(ailp, tail_lsn); } /* Insert a log item into the AIL. */ void xfs_trans_ail_insert( struct xfs_ail *ailp, struct xfs_log_item *lip, xfs_lsn_t lsn) { spin_lock(&ailp->ail_lock); xfs_trans_ail_update_bulk(ailp, NULL, &lip, 1, lsn); } /* * Delete one log item from the AIL. * * If this item was at the tail of the AIL, return the LSN of the log item so * that we can use it to check if the LSN of the tail of the log has moved * when finishing up the AIL delete process in xfs_ail_update_finish(). */ xfs_lsn_t xfs_ail_delete_one( struct xfs_ail *ailp, struct xfs_log_item *lip) { struct xfs_log_item *mlip = xfs_ail_min(ailp); xfs_lsn_t lsn = lip->li_lsn; trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn); xfs_ail_delete(ailp, lip); clear_bit(XFS_LI_IN_AIL, &lip->li_flags); lip->li_lsn = 0; if (mlip == lip) return lsn; return 0; } void xfs_trans_ail_delete( struct xfs_log_item *lip, int shutdown_type) { struct xfs_ail *ailp = lip->li_ailp; struct xlog *log = ailp->ail_log; xfs_lsn_t tail_lsn; spin_lock(&ailp->ail_lock); if (!test_bit(XFS_LI_IN_AIL, &lip->li_flags)) { spin_unlock(&ailp->ail_lock); if (shutdown_type && !xlog_is_shutdown(log)) { xfs_alert_tag(log->l_mp, XFS_PTAG_AILDELETE, "%s: attempting to delete a log item that is not in the AIL", __func__); xlog_force_shutdown(log, shutdown_type); } return; } /* xfs_ail_update_finish() drops the AIL lock */ xfs_clear_li_failed(lip); tail_lsn = xfs_ail_delete_one(ailp, lip); xfs_ail_update_finish(ailp, tail_lsn); } int xfs_trans_ail_init( xfs_mount_t *mp) { struct xfs_ail *ailp; ailp = kzalloc(sizeof(struct xfs_ail), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!ailp) return -ENOMEM; ailp->ail_log = mp->m_log; INIT_LIST_HEAD(&ailp->ail_head); INIT_LIST_HEAD(&ailp->ail_cursors); spin_lock_init(&ailp->ail_lock); INIT_LIST_HEAD(&ailp->ail_buf_list); init_waitqueue_head(&ailp->ail_empty); ailp->ail_task = kthread_run(xfsaild, ailp, "xfsaild/%s", mp->m_super->s_id); if (IS_ERR(ailp->ail_task)) goto out_free_ailp; mp->m_ail = ailp; return 0; out_free_ailp: kfree(ailp); return -ENOMEM; } void xfs_trans_ail_destroy( xfs_mount_t *mp) { struct xfs_ail *ailp = mp->m_ail; kthread_stop(ailp->ail_task); kfree(ailp); } |
| 2 2 1 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 | // SPDX-License-Identifier: GPL-2.0 /* * Author: Andrei Vagin <avagin@openvz.org> * Author: Dmitry Safonov <dima@arista.com> */ #include <linux/time_namespace.h> #include <linux/user_namespace.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/clocksource.h> #include <linux/seq_file.h> #include <linux/proc_ns.h> #include <linux/export.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/err.h> #include <linux/mm.h> #include <vdso/datapage.h> ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, struct timens_offsets *ns_offsets) { ktime_t offset; switch (clockid) { case CLOCK_MONOTONIC: offset = timespec64_to_ktime(ns_offsets->monotonic); break; case CLOCK_BOOTTIME: case CLOCK_BOOTTIME_ALARM: offset = timespec64_to_ktime(ns_offsets->boottime); break; default: return tim; } /* * Check that @tim value is in [offset, KTIME_MAX + offset] * and subtract offset. */ if (tim < offset) { /* * User can specify @tim *absolute* value - if it's lesser than * the time namespace's offset - it's already expired. */ tim = 0; } else { tim = ktime_sub(tim, offset); if (unlikely(tim > KTIME_MAX)) tim = KTIME_MAX; } return tim; } static struct ucounts *inc_time_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_TIME_NAMESPACES); } static void dec_time_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_TIME_NAMESPACES); } /** * clone_time_ns - Clone a time namespace * @user_ns: User namespace which owns a new namespace. * @old_ns: Namespace to clone * * Clone @old_ns and set the clone refcount to 1 * * Return: The new namespace or ERR_PTR. */ static struct time_namespace *clone_time_ns(struct user_namespace *user_ns, struct time_namespace *old_ns) { struct time_namespace *ns; struct ucounts *ucounts; int err; err = -ENOSPC; ucounts = inc_time_namespaces(user_ns); if (!ucounts) goto fail; err = -ENOMEM; ns = kmalloc(sizeof(*ns), GFP_KERNEL_ACCOUNT); if (!ns) goto fail_dec; refcount_set(&ns->ns.count, 1); ns->vvar_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!ns->vvar_page) goto fail_free; err = ns_alloc_inum(&ns->ns); if (err) goto fail_free_page; ns->ucounts = ucounts; ns->ns.ops = &timens_operations; ns->user_ns = get_user_ns(user_ns); ns->offsets = old_ns->offsets; ns->frozen_offsets = false; return ns; fail_free_page: __free_page(ns->vvar_page); fail_free: kfree(ns); fail_dec: dec_time_namespaces(ucounts); fail: return ERR_PTR(err); } /** * copy_time_ns - Create timens_for_children from @old_ns * @flags: Cloning flags * @user_ns: User namespace which owns a new namespace. * @old_ns: Namespace to clone * * If CLONE_NEWTIME specified in @flags, creates a new timens_for_children; * adds a refcounter to @old_ns otherwise. * * Return: timens_for_children namespace or ERR_PTR. */ struct time_namespace *copy_time_ns(unsigned long flags, struct user_namespace *user_ns, struct time_namespace *old_ns) { if (!(flags & CLONE_NEWTIME)) return get_time_ns(old_ns); return clone_time_ns(user_ns, old_ns); } static struct timens_offset offset_from_ts(struct timespec64 off) { struct timens_offset ret; ret.sec = off.tv_sec; ret.nsec = off.tv_nsec; return ret; } /* * A time namespace VVAR page has the same layout as the VVAR page which * contains the system wide VDSO data. * * For a normal task the VVAR pages are installed in the normal ordering: * VVAR * PVCLOCK * HVCLOCK * TIMENS <- Not really required * * Now for a timens task the pages are installed in the following order: * TIMENS * PVCLOCK * HVCLOCK * VVAR * * The check for vdso_data->clock_mode is in the unlikely path of * the seq begin magic. So for the non-timens case most of the time * 'seq' is even, so the branch is not taken. * * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check * for vdso_data->clock_mode is a non-issue. The task is spin waiting for the * update to finish and for 'seq' to become even anyway. * * Timens page has vdso_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which * enforces the time namespace handling path. */ static void timens_setup_vdso_data(struct vdso_data *vdata, struct time_namespace *ns) { struct timens_offset *offset = vdata->offset; struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic); struct timens_offset boottime = offset_from_ts(ns->offsets.boottime); vdata->seq = 1; vdata->clock_mode = VDSO_CLOCKMODE_TIMENS; offset[CLOCK_MONOTONIC] = monotonic; offset[CLOCK_MONOTONIC_RAW] = monotonic; offset[CLOCK_MONOTONIC_COARSE] = monotonic; offset[CLOCK_BOOTTIME] = boottime; offset[CLOCK_BOOTTIME_ALARM] = boottime; } struct page *find_timens_vvar_page(struct vm_area_struct *vma) { if (likely(vma->vm_mm == current->mm)) return current->nsproxy->time_ns->vvar_page; /* * VM_PFNMAP | VM_IO protect .fault() handler from being called * through interfaces like /proc/$pid/mem or * process_vm_{readv,writev}() as long as there's no .access() * in special_mapping_vmops(). * For more details check_vma_flags() and __access_remote_vm() */ WARN(1, "vvar_page accessed remotely"); return NULL; } /* * Protects possibly multiple offsets writers racing each other * and tasks entering the namespace. */ static DEFINE_MUTEX(offset_lock); static void timens_set_vvar_page(struct task_struct *task, struct time_namespace *ns) { struct vdso_data *vdata; unsigned int i; if (ns == &init_time_ns) return; /* Fast-path, taken by every task in namespace except the first. */ if (likely(ns->frozen_offsets)) return; mutex_lock(&offset_lock); /* Nothing to-do: vvar_page has been already initialized. */ if (ns->frozen_offsets) goto out; ns->frozen_offsets = true; vdata = arch_get_vdso_data(page_address(ns->vvar_page)); for (i = 0; i < CS_BASES; i++) timens_setup_vdso_data(&vdata[i], ns); out: mutex_unlock(&offset_lock); } void free_time_ns(struct time_namespace *ns) { dec_time_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); __free_page(ns->vvar_page); kfree(ns); } static struct time_namespace *to_time_ns(struct ns_common *ns) { return container_of(ns, struct time_namespace, ns); } static struct ns_common *timens_get(struct task_struct *task) { struct time_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->time_ns; get_time_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static struct ns_common *timens_for_children_get(struct task_struct *task) { struct time_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->time_ns_for_children; get_time_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static void timens_put(struct ns_common *ns) { put_time_ns(to_time_ns(ns)); } void timens_commit(struct task_struct *tsk, struct time_namespace *ns) { timens_set_vvar_page(tsk, ns); vdso_join_timens(tsk, ns); } static int timens_install(struct nsset *nsset, struct ns_common *new) { struct nsproxy *nsproxy = nsset->nsproxy; struct time_namespace *ns = to_time_ns(new); if (!current_is_single_threaded()) return -EUSERS; if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; get_time_ns(ns); put_time_ns(nsproxy->time_ns); nsproxy->time_ns = ns; get_time_ns(ns); put_time_ns(nsproxy->time_ns_for_children); nsproxy->time_ns_for_children = ns; return 0; } void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) { struct ns_common *nsc = &nsproxy->time_ns_for_children->ns; struct time_namespace *ns = to_time_ns(nsc); /* create_new_namespaces() already incremented the ref counter */ if (nsproxy->time_ns == nsproxy->time_ns_for_children) return; get_time_ns(ns); put_time_ns(nsproxy->time_ns); nsproxy->time_ns = ns; timens_commit(tsk, ns); } static struct user_namespace *timens_owner(struct ns_common *ns) { return to_time_ns(ns)->user_ns; } static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts) { char *clock; switch (clockid) { case CLOCK_BOOTTIME: clock = "boottime"; break; case CLOCK_MONOTONIC: clock = "monotonic"; break; default: clock = "unknown"; break; } seq_printf(m, "%-10s %10lld %9ld\n", clock, ts->tv_sec, ts->tv_nsec); } void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m) { struct ns_common *ns; struct time_namespace *time_ns; ns = timens_for_children_get(p); if (!ns) return; time_ns = to_time_ns(ns); show_offset(m, CLOCK_MONOTONIC, &time_ns->offsets.monotonic); show_offset(m, CLOCK_BOOTTIME, &time_ns->offsets.boottime); put_time_ns(time_ns); } int proc_timens_set_offset(struct file *file, struct task_struct *p, struct proc_timens_offset *offsets, int noffsets) { struct ns_common *ns; struct time_namespace *time_ns; struct timespec64 tp; int i, err; ns = timens_for_children_get(p); if (!ns) return -ESRCH; time_ns = to_time_ns(ns); if (!file_ns_capable(file, time_ns->user_ns, CAP_SYS_TIME)) { put_time_ns(time_ns); return -EPERM; } for (i = 0; i < noffsets; i++) { struct proc_timens_offset *off = &offsets[i]; switch (off->clockid) { case CLOCK_MONOTONIC: ktime_get_ts64(&tp); break; case CLOCK_BOOTTIME: ktime_get_boottime_ts64(&tp); break; default: err = -EINVAL; goto out; } err = -ERANGE; if (off->val.tv_sec > KTIME_SEC_MAX || off->val.tv_sec < -KTIME_SEC_MAX) goto out; tp = timespec64_add(tp, off->val); /* * KTIME_SEC_MAX is divided by 2 to be sure that KTIME_MAX is * still unreachable. */ if (tp.tv_sec < 0 || tp.tv_sec > KTIME_SEC_MAX / 2) goto out; } mutex_lock(&offset_lock); if (time_ns->frozen_offsets) { err = -EACCES; goto out_unlock; } err = 0; /* Don't report errors after this line */ for (i = 0; i < noffsets; i++) { struct proc_timens_offset *off = &offsets[i]; struct timespec64 *offset = NULL; switch (off->clockid) { case CLOCK_MONOTONIC: offset = &time_ns->offsets.monotonic; break; case CLOCK_BOOTTIME: offset = &time_ns->offsets.boottime; break; } *offset = off->val; } out_unlock: mutex_unlock(&offset_lock); out: put_time_ns(time_ns); return err; } const struct proc_ns_operations timens_operations = { .name = "time", .type = CLONE_NEWTIME, .get = timens_get, .put = timens_put, .install = timens_install, .owner = timens_owner, }; const struct proc_ns_operations timens_for_children_operations = { .name = "time_for_children", .real_ns_name = "time", .type = CLONE_NEWTIME, .get = timens_for_children_get, .put = timens_put, .install = timens_install, .owner = timens_owner, }; struct time_namespace init_time_ns = { .ns.count = REFCOUNT_INIT(3), .user_ns = &init_user_ns, .ns.inum = PROC_TIME_INIT_INO, .ns.ops = &timens_operations, .frozen_offsets = true, }; |
| 12 2 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright 1997-1998 Transmeta Corporation - All Rights Reserved * Copyright 2005-2006 Ian Kent <raven@themaw.net> */ /* Internal header file for autofs */ #include <linux/auto_fs.h> #include <linux/auto_dev-ioctl.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/string.h> #include <linux/wait.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/list.h> #include <linux/completion.h> #include <linux/file.h> #include <linux/magic.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> /* This is the range of ioctl() numbers we claim as ours */ #define AUTOFS_IOC_FIRST AUTOFS_IOC_READY #define AUTOFS_IOC_COUNT 32 #define AUTOFS_DEV_IOCTL_IOC_FIRST (AUTOFS_DEV_IOCTL_VERSION) #define AUTOFS_DEV_IOCTL_IOC_COUNT \ (AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD - AUTOFS_DEV_IOCTL_VERSION_CMD) #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) KBUILD_MODNAME ":pid:%d:%s: " fmt, current->pid, __func__ extern struct file_system_type autofs_fs_type; /* * Unified info structure. This is pointed to by both the dentry and * inode structures. Each file in the filesystem has an instance of this * structure. It holds a reference to the dentry, so dentries are never * flushed while the file exists. All name lookups are dealt with at the * dentry level, although the filesystem can interfere in the validation * process. Readdir is implemented by traversing the dentry lists. */ struct autofs_info { struct dentry *dentry; int flags; struct completion expire_complete; struct list_head active; struct list_head expiring; struct autofs_sb_info *sbi; unsigned long last_used; int count; kuid_t uid; kgid_t gid; struct rcu_head rcu; }; #define AUTOFS_INF_EXPIRING (1<<0) /* dentry in the process of expiring */ #define AUTOFS_INF_WANT_EXPIRE (1<<1) /* the dentry is being considered * for expiry, so RCU_walk is * not permitted. If it progresses to * actual expiry attempt, the flag is * not cleared when EXPIRING is set - * in that case it gets cleared only * when it comes to clearing EXPIRING. */ #define AUTOFS_INF_PENDING (1<<2) /* dentry pending mount */ struct autofs_wait_queue { wait_queue_head_t queue; struct autofs_wait_queue *next; autofs_wqt_t wait_queue_token; /* We use the following to see what we are waiting for */ struct qstr name; u32 offset; u32 dev; u64 ino; kuid_t uid; kgid_t gid; pid_t pid; pid_t tgid; /* This is for status reporting upon return */ int status; unsigned int wait_ctr; }; #define AUTOFS_SBI_MAGIC 0x6d4a556d #define AUTOFS_SBI_CATATONIC 0x0001 #define AUTOFS_SBI_STRICTEXPIRE 0x0002 #define AUTOFS_SBI_IGNORE 0x0004 struct autofs_sb_info { u32 magic; int pipefd; struct file *pipe; struct pid *oz_pgrp; int version; int sub_version; int min_proto; int max_proto; unsigned int flags; unsigned long exp_timeout; unsigned int type; struct super_block *sb; struct mutex wq_mutex; struct mutex pipe_mutex; spinlock_t fs_lock; struct autofs_wait_queue *queues; /* Wait queue pointer */ spinlock_t lookup_lock; struct list_head active_list; struct list_head expiring_list; struct rcu_head rcu; }; static inline struct autofs_sb_info *autofs_sbi(struct super_block *sb) { return (struct autofs_sb_info *)(sb->s_fs_info); } static inline struct autofs_info *autofs_dentry_ino(struct dentry *dentry) { return (struct autofs_info *)(dentry->d_fsdata); } /* autofs_oz_mode(): do we see the man behind the curtain? (The * processes which do manipulations for us in user space sees the raw * filesystem without "magic".) */ static inline int autofs_oz_mode(struct autofs_sb_info *sbi) { return ((sbi->flags & AUTOFS_SBI_CATATONIC) || task_pgrp(current) == sbi->oz_pgrp); } static inline bool autofs_empty(struct autofs_info *ino) { return ino->count < 2; } struct inode *autofs_get_inode(struct super_block *, umode_t); void autofs_free_ino(struct autofs_info *); /* Expiration */ int is_autofs_dentry(struct dentry *); int autofs_expire_wait(const struct path *path, int rcu_walk); int autofs_expire_run(struct super_block *, struct vfsmount *, struct autofs_sb_info *, struct autofs_packet_expire __user *); int autofs_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, struct autofs_sb_info *sbi, unsigned int how); int autofs_expire_multi(struct super_block *, struct vfsmount *, struct autofs_sb_info *, int __user *); /* Device node initialization */ int autofs_dev_ioctl_init(void); void autofs_dev_ioctl_exit(void); /* Operations structures */ extern const struct inode_operations autofs_symlink_inode_operations; extern const struct inode_operations autofs_dir_inode_operations; extern const struct file_operations autofs_dir_operations; extern const struct file_operations autofs_root_operations; extern const struct dentry_operations autofs_dentry_operations; /* VFS automount flags management functions */ static inline void __managed_dentry_set_managed(struct dentry *dentry) { dentry->d_flags |= (DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT); } static inline void managed_dentry_set_managed(struct dentry *dentry) { spin_lock(&dentry->d_lock); __managed_dentry_set_managed(dentry); spin_unlock(&dentry->d_lock); } static inline void __managed_dentry_clear_managed(struct dentry *dentry) { dentry->d_flags &= ~(DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT); } static inline void managed_dentry_clear_managed(struct dentry *dentry) { spin_lock(&dentry->d_lock); __managed_dentry_clear_managed(dentry); spin_unlock(&dentry->d_lock); } /* Initializing function */ extern const struct fs_parameter_spec autofs_param_specs[]; int autofs_init_fs_context(struct fs_context *fc); struct autofs_info *autofs_new_ino(struct autofs_sb_info *); void autofs_clean_ino(struct autofs_info *); static inline int autofs_check_pipe(struct file *pipe) { if (!(pipe->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (!S_ISFIFO(file_inode(pipe)->i_mode)) return -EINVAL; return 0; } static inline void autofs_set_packet_pipe_flags(struct file *pipe) { /* We want a packet pipe */ pipe->f_flags |= O_DIRECT; /* We don't expect -EAGAIN */ pipe->f_flags &= ~O_NONBLOCK; } static inline int autofs_prepare_pipe(struct file *pipe) { int ret = autofs_check_pipe(pipe); if (ret < 0) return ret; autofs_set_packet_pipe_flags(pipe); return 0; } /* Queue management functions */ int autofs_wait(struct autofs_sb_info *, const struct path *, enum autofs_notify); int autofs_wait_release(struct autofs_sb_info *, autofs_wqt_t, int); void autofs_catatonic_mode(struct autofs_sb_info *); static inline u32 autofs_get_dev(struct autofs_sb_info *sbi) { return new_encode_dev(sbi->sb->s_dev); } static inline u64 autofs_get_ino(struct autofs_sb_info *sbi) { return d_inode(sbi->sb->s_root)->i_ino; } static inline void __autofs_add_expiring(struct dentry *dentry) { struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); if (ino) { if (list_empty(&ino->expiring)) list_add(&ino->expiring, &sbi->expiring_list); } } static inline void autofs_add_expiring(struct dentry *dentry) { struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); if (ino) { spin_lock(&sbi->lookup_lock); if (list_empty(&ino->expiring)) list_add(&ino->expiring, &sbi->expiring_list); spin_unlock(&sbi->lookup_lock); } } static inline void autofs_del_expiring(struct dentry *dentry) { struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); if (ino) { spin_lock(&sbi->lookup_lock); if (!list_empty(&ino->expiring)) list_del_init(&ino->expiring); spin_unlock(&sbi->lookup_lock); } } void autofs_kill_sb(struct super_block *); |
| 63 62 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/partitions/sun.c * * Code extracted from drivers/block/genhd.c * * Copyright (C) 1991-1998 Linus Torvalds * Re-organised Feb 1998 Russell King */ #include "check.h" #define SUN_LABEL_MAGIC 0xDABE #define SUN_VTOC_SANITY 0x600DDEEE enum { SUN_WHOLE_DISK = 5, LINUX_RAID_PARTITION = 0xfd, /* autodetect RAID partition */ }; int sun_partition(struct parsed_partitions *state) { int i; __be16 csum; int slot = 1; __be16 *ush; Sector sect; struct sun_disklabel { unsigned char info[128]; /* Informative text string */ struct sun_vtoc { __be32 version; /* Layout version */ char volume[8]; /* Volume name */ __be16 nparts; /* Number of partitions */ struct sun_info { /* Partition hdrs, sec 2 */ __be16 id; __be16 flags; } infos[8]; __be16 padding; /* Alignment padding */ __be32 bootinfo[3]; /* Info needed by mboot */ __be32 sanity; /* To verify vtoc sanity */ __be32 reserved[10]; /* Free space */ __be32 timestamp[8]; /* Partition timestamp */ } vtoc; __be32 write_reinstruct; /* sectors to skip, writes */ __be32 read_reinstruct; /* sectors to skip, reads */ unsigned char spare[148]; /* Padding */ __be16 rspeed; /* Disk rotational speed */ __be16 pcylcount; /* Physical cylinder count */ __be16 sparecyl; /* extra sects per cylinder */ __be16 obs1; /* gap1 */ __be16 obs2; /* gap2 */ __be16 ilfact; /* Interleave factor */ __be16 ncyl; /* Data cylinder count */ __be16 nacyl; /* Alt. cylinder count */ __be16 ntrks; /* Tracks per cylinder */ __be16 nsect; /* Sectors per track */ __be16 obs3; /* bhead - Label head offset */ __be16 obs4; /* ppart - Physical Partition */ struct sun_partition { __be32 start_cylinder; __be32 num_sectors; } partitions[8]; __be16 magic; /* Magic number */ __be16 csum; /* Label xor'd checksum */ } * label; struct sun_partition *p; unsigned long spc; int use_vtoc; int nparts; label = read_part_sector(state, 0, §); if (!label) return -1; p = label->partitions; if (be16_to_cpu(label->magic) != SUN_LABEL_MAGIC) { /* printk(KERN_INFO "Dev %s Sun disklabel: bad magic %04x\n", state->disk->disk_name, be16_to_cpu(label->magic)); */ put_dev_sector(sect); return 0; } /* Look at the checksum */ ush = ((__be16 *) (label+1)) - 1; for (csum = 0; ush >= ((__be16 *) label);) csum ^= *ush--; if (csum) { printk("Dev %s Sun disklabel: Csum bad, label corrupted\n", state->disk->disk_name); put_dev_sector(sect); return 0; } /* Check to see if we can use the VTOC table */ use_vtoc = ((be32_to_cpu(label->vtoc.sanity) == SUN_VTOC_SANITY) && (be32_to_cpu(label->vtoc.version) == 1) && (be16_to_cpu(label->vtoc.nparts) <= 8)); /* Use 8 partition entries if not specified in validated VTOC */ nparts = (use_vtoc) ? be16_to_cpu(label->vtoc.nparts) : 8; /* * So that old Linux-Sun partitions continue to work, * alow the VTOC to be used under the additional condition ... */ use_vtoc = use_vtoc || !(label->vtoc.sanity || label->vtoc.version || label->vtoc.nparts); spc = be16_to_cpu(label->ntrks) * be16_to_cpu(label->nsect); for (i = 0; i < nparts; i++, p++) { unsigned long st_sector; unsigned int num_sectors; st_sector = be32_to_cpu(p->start_cylinder) * spc; num_sectors = be32_to_cpu(p->num_sectors); if (num_sectors) { put_partition(state, slot, st_sector, num_sectors); state->parts[slot].flags = 0; if (use_vtoc) { if (be16_to_cpu(label->vtoc.infos[i].id) == LINUX_RAID_PARTITION) state->parts[slot].flags |= ADDPART_FLAG_RAID; else if (be16_to_cpu(label->vtoc.infos[i].id) == SUN_WHOLE_DISK) state->parts[slot].flags |= ADDPART_FLAG_WHOLEDISK; } } slot++; } strlcat(state->pp_buf, "\n", PAGE_SIZE); put_dev_sector(sect); return 1; } |
| 6758 6751 4216 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/init.h> #include <linux/export.h> #include <linux/timer.h> #include <linux/acpi_pmtmr.h> #include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/clocksource.h> #include <linux/percpu.h> #include <linux/timex.h> #include <linux/static_key.h> #include <linux/static_call.h> #include <asm/hpet.h> #include <asm/timer.h> #include <asm/vgtod.h> #include <asm/time.h> #include <asm/delay.h> #include <asm/hypervisor.h> #include <asm/nmi.h> #include <asm/x86_init.h> #include <asm/geode.h> #include <asm/apic.h> #include <asm/cpu_device_id.h> #include <asm/i8259.h> #include <asm/uv/uv.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); unsigned int __read_mostly tsc_khz; EXPORT_SYMBOL(tsc_khz); #define KHZ 1000 /* * TSC can be unstable due to cpufreq or due to unsynced TSCs */ static int __read_mostly tsc_unstable; static unsigned int __initdata tsc_early_khz; static DEFINE_STATIC_KEY_FALSE_RO(__use_tsc); int tsc_clocksource_reliable; static int __read_mostly tsc_force_recalibrate; static struct clocksource_base art_base_clk = { .id = CSID_X86_ART, }; static bool have_art; struct cyc2ns { struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ seqcount_latch_t seq; /* 32 + 4 = 36 */ }; /* fits one cacheline */ static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); static int __init tsc_early_khz_setup(char *buf) { return kstrtouint(buf, 0, &tsc_early_khz); } early_param("tsc_early_khz", tsc_early_khz_setup); __always_inline void __cyc2ns_read(struct cyc2ns_data *data) { int seq, idx; do { seq = this_cpu_read(cyc2ns.seq.seqcount.sequence); idx = seq & 1; data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset); data->cyc2ns_mul = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul); data->cyc2ns_shift = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift); } while (unlikely(seq != this_cpu_read(cyc2ns.seq.seqcount.sequence))); } __always_inline void cyc2ns_read_begin(struct cyc2ns_data *data) { preempt_disable_notrace(); __cyc2ns_read(data); } __always_inline void cyc2ns_read_end(void) { preempt_enable_notrace(); } /* * Accelerators for sched_clock() * convert from cycles(64bits) => nanoseconds (64bits) * basic equation: * ns = cycles / (freq / ns_per_sec) * ns = cycles * (ns_per_sec / freq) * ns = cycles * (10^9 / (cpu_khz * 10^3)) * ns = cycles * (10^6 / cpu_khz) * * Then we use scaling math (suggested by george@mvista.com) to get: * ns = cycles * (10^6 * SC / cpu_khz) / SC * ns = cycles * cyc2ns_scale / SC * * And since SC is a constant power of two, we can convert the div * into a shift. The larger SC is, the more accurate the conversion, but * cyc2ns_scale needs to be a 32-bit value so that 32-bit multiplication * (64-bit result) can be used. * * We can use khz divisor instead of mhz to keep a better precision. * (mathieu.desnoyers@polymtl.ca) * * -johnstul@us.ibm.com "math is hard, lets go shopping!" */ static __always_inline unsigned long long __cycles_2_ns(unsigned long long cyc) { struct cyc2ns_data data; unsigned long long ns; __cyc2ns_read(&data); ns = data.cyc2ns_offset; ns += mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift); return ns; } static __always_inline unsigned long long cycles_2_ns(unsigned long long cyc) { unsigned long long ns; preempt_disable_notrace(); ns = __cycles_2_ns(cyc); preempt_enable_notrace(); return ns; } static void __set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { unsigned long long ns_now; struct cyc2ns_data data; struct cyc2ns *c2n; ns_now = cycles_2_ns(tsc_now); /* * Compute a new multiplier as per the above comment and ensure our * time function is continuous; see the comment near struct * cyc2ns_data. */ clocks_calc_mult_shift(&data.cyc2ns_mul, &data.cyc2ns_shift, khz, NSEC_PER_MSEC, 0); /* * cyc2ns_shift is exported via arch_perf_update_userpage() where it is * not expected to be greater than 31 due to the original published * conversion algorithm shifting a 32-bit value (now specifies a 64-bit * value) - refer perf_event_mmap_page documentation in perf_event.h. */ if (data.cyc2ns_shift == 32) { data.cyc2ns_shift = 31; data.cyc2ns_mul >>= 1; } data.cyc2ns_offset = ns_now - mul_u64_u32_shr(tsc_now, data.cyc2ns_mul, data.cyc2ns_shift); c2n = per_cpu_ptr(&cyc2ns, cpu); raw_write_seqcount_latch(&c2n->seq); c2n->data[0] = data; raw_write_seqcount_latch(&c2n->seq); c2n->data[1] = data; } static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { unsigned long flags; local_irq_save(flags); sched_clock_idle_sleep_event(); if (khz) __set_cyc2ns_scale(khz, cpu, tsc_now); sched_clock_idle_wakeup_event(); local_irq_restore(flags); } /* * Initialize cyc2ns for boot cpu */ static void __init cyc2ns_init_boot_cpu(void) { struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns); seqcount_latch_init(&c2n->seq); __set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc()); } /* * Secondary CPUs do not run through tsc_init(), so set up * all the scale factors for all CPUs, assuming the same * speed as the bootup CPU. */ static void __init cyc2ns_init_secondary_cpus(void) { unsigned int cpu, this_cpu = smp_processor_id(); struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns); struct cyc2ns_data *data = c2n->data; for_each_possible_cpu(cpu) { if (cpu != this_cpu) { seqcount_latch_init(&c2n->seq); c2n = per_cpu_ptr(&cyc2ns, cpu); c2n->data[0] = data[0]; c2n->data[1] = data[1]; } } } /* * Scheduler clock - returns current time in nanosec units. */ noinstr u64 native_sched_clock(void) { if (static_branch_likely(&__use_tsc)) { u64 tsc_now = rdtsc(); /* return the value in ns */ return __cycles_2_ns(tsc_now); } /* * Fall back to jiffies if there's no TSC available: * ( But note that we still use it if the TSC is marked * unstable. We do this because unlike Time Of Day, * the scheduler clock tolerates small errors and it's * very important for it to be as fast as the platform * can achieve it. ) */ /* No locking but a rare wrong value is not a big deal: */ return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); } /* * Generate a sched_clock if you already have a TSC value. */ u64 native_sched_clock_from_tsc(u64 tsc) { return cycles_2_ns(tsc); } /* We need to define a real function for sched_clock, to override the weak default version */ #ifdef CONFIG_PARAVIRT noinstr u64 sched_clock_noinstr(void) { return paravirt_sched_clock(); } bool using_native_sched_clock(void) { return static_call_query(pv_sched_clock) == native_sched_clock; } #else u64 sched_clock_noinstr(void) __attribute__((alias("native_sched_clock"))); bool using_native_sched_clock(void) { return true; } #endif notrace u64 sched_clock(void) { u64 now; preempt_disable_notrace(); now = sched_clock_noinstr(); preempt_enable_notrace(); return now; } int check_tsc_unstable(void) { return tsc_unstable; } EXPORT_SYMBOL_GPL(check_tsc_unstable); #ifdef CONFIG_X86_TSC int __init notsc_setup(char *str) { mark_tsc_unstable("boot parameter notsc"); return 1; } #else /* * disable flag for tsc. Takes effect by clearing the TSC cpu flag * in cpu/common.c */ int __init notsc_setup(char *str) { setup_clear_cpu_cap(X86_FEATURE_TSC); return 1; } #endif __setup("notsc", notsc_setup); static int no_sched_irq_time; static int no_tsc_watchdog; static int tsc_as_watchdog; static int __init tsc_setup(char *str) { if (!strcmp(str, "reliable")) tsc_clocksource_reliable = 1; if (!strncmp(str, "noirqtime", 9)) no_sched_irq_time = 1; if (!strcmp(str, "unstable")) mark_tsc_unstable("boot parameter"); if (!strcmp(str, "nowatchdog")) { no_tsc_watchdog = 1; if (tsc_as_watchdog) pr_alert("%s: Overriding earlier tsc=watchdog with tsc=nowatchdog\n", __func__); tsc_as_watchdog = 0; } if (!strcmp(str, "recalibrate")) tsc_force_recalibrate = 1; if (!strcmp(str, "watchdog")) { if (no_tsc_watchdog) pr_alert("%s: tsc=watchdog overridden by earlier tsc=nowatchdog\n", __func__); else tsc_as_watchdog = 1; } return 1; } __setup("tsc=", tsc_setup); #define MAX_RETRIES 5 #define TSC_DEFAULT_THRESHOLD 0x20000 /* * Read TSC and the reference counters. Take care of any disturbances */ static u64 tsc_read_refs(u64 *p, int hpet) { u64 t1, t2; u64 thresh = tsc_khz ? tsc_khz >> 5 : TSC_DEFAULT_THRESHOLD; int i; for (i = 0; i < MAX_RETRIES; i++) { t1 = get_cycles(); if (hpet) *p = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF; else *p = acpi_pm_read_early(); t2 = get_cycles(); if ((t2 - t1) < thresh) return t2; } return ULLONG_MAX; } /* * Calculate the TSC frequency from HPET reference */ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2) { u64 tmp; if (hpet2 < hpet1) hpet2 += 0x100000000ULL; hpet2 -= hpet1; tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD)); do_div(tmp, 1000000); deltatsc = div64_u64(deltatsc, tmp); return (unsigned long) deltatsc; } /* * Calculate the TSC frequency from PMTimer reference */ static unsigned long calc_pmtimer_ref(u64 deltatsc, u64 pm1, u64 pm2) { u64 tmp; if (!pm1 && !pm2) return ULONG_MAX; if (pm2 < pm1) pm2 += (u64)ACPI_PM_OVRRUN; pm2 -= pm1; tmp = pm2 * 1000000000LL; do_div(tmp, PMTMR_TICKS_PER_SEC); do_div(deltatsc, tmp); return (unsigned long) deltatsc; } #define CAL_MS 10 #define CAL_LATCH (PIT_TICK_RATE / (1000 / CAL_MS)) #define CAL_PIT_LOOPS 1000 #define CAL2_MS 50 #define CAL2_LATCH (PIT_TICK_RATE / (1000 / CAL2_MS)) #define CAL2_PIT_LOOPS 5000 /* * Try to calibrate the TSC against the Programmable * Interrupt Timer and return the frequency of the TSC * in kHz. * * Return ULONG_MAX on failure to calibrate. */ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin) { u64 tsc, t1, t2, delta; unsigned long tscmin, tscmax; int pitcnt; if (!has_legacy_pic()) { /* * Relies on tsc_early_delay_calibrate() to have given us semi * usable udelay(), wait for the same 50ms we would have with * the PIT loop below. */ udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); return ULONG_MAX; } /* Set the Gate high, disable speaker */ outb((inb(0x61) & ~0x02) | 0x01, 0x61); /* * Setup CTC channel 2* for mode 0, (interrupt on terminal * count mode), binary count. Set the latch register to 50ms * (LSB then MSB) to begin countdown. */ outb(0xb0, 0x43); outb(latch & 0xff, 0x42); outb(latch >> 8, 0x42); tsc = t1 = t2 = get_cycles(); pitcnt = 0; tscmax = 0; tscmin = ULONG_MAX; while ((inb(0x61) & 0x20) == 0) { t2 = get_cycles(); delta = t2 - tsc; tsc = t2; if ((unsigned long) delta < tscmin) tscmin = (unsigned int) delta; if ((unsigned long) delta > tscmax) tscmax = (unsigned int) delta; pitcnt++; } /* * Sanity checks: * * If we were not able to read the PIT more than loopmin * times, then we have been hit by a massive SMI * * If the maximum is 10 times larger than the minimum, * then we got hit by an SMI as well. */ if (pitcnt < loopmin || tscmax > 10 * tscmin) return ULONG_MAX; /* Calculate the PIT value */ delta = t2 - t1; do_div(delta, ms); return delta; } /* * This reads the current MSB of the PIT counter, and * checks if we are running on sufficiently fast and * non-virtualized hardware. * * Our expectations are: * * - the PIT is running at roughly 1.19MHz * * - each IO is going to take about 1us on real hardware, * but we allow it to be much faster (by a factor of 10) or * _slightly_ slower (ie we allow up to a 2us read+counter * update - anything else implies a unacceptably slow CPU * or PIT for the fast calibration to work. * * - with 256 PIT ticks to read the value, we have 214us to * see the same MSB (and overhead like doing a single TSC * read per MSB value etc). * * - We're doing 2 reads per loop (LSB, MSB), and we expect * them each to take about a microsecond on real hardware. * So we expect a count value of around 100. But we'll be * generous, and accept anything over 50. * * - if the PIT is stuck, and we see *many* more reads, we * return early (and the next caller of pit_expect_msb() * then consider it a failure when they don't see the * next expected value). * * These expectations mean that we know that we have seen the * transition from one expected value to another with a fairly * high accuracy, and we didn't miss any events. We can thus * use the TSC value at the transitions to calculate a pretty * good value for the TSC frequency. */ static inline int pit_verify_msb(unsigned char val) { /* Ignore LSB */ inb(0x42); return inb(0x42) == val; } static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap) { int count; u64 tsc = 0, prev_tsc = 0; for (count = 0; count < 50000; count++) { if (!pit_verify_msb(val)) break; prev_tsc = tsc; tsc = get_cycles(); } *deltap = get_cycles() - prev_tsc; *tscp = tsc; /* * We require _some_ success, but the quality control * will be based on the error terms on the TSC values. */ return count > 5; } /* * How many MSB values do we want to see? We aim for * a maximum error rate of 500ppm (in practice the * real error is much smaller), but refuse to spend * more than 50ms on it. */ #define MAX_QUICK_PIT_MS 50 #define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256) static unsigned long quick_pit_calibrate(void) { int i; u64 tsc, delta; unsigned long d1, d2; if (!has_legacy_pic()) return 0; /* Set the Gate high, disable speaker */ outb((inb(0x61) & ~0x02) | 0x01, 0x61); /* * Counter 2, mode 0 (one-shot), binary count * * NOTE! Mode 2 decrements by two (and then the * output is flipped each time, giving the same * final output frequency as a decrement-by-one), * so mode 0 is much better when looking at the * individual counts. */ outb(0xb0, 0x43); /* Start at 0xffff */ outb(0xff, 0x42); outb(0xff, 0x42); /* * The PIT starts counting at the next edge, so we * need to delay for a microsecond. The easiest way * to do that is to just read back the 16-bit counter * once from the PIT. */ pit_verify_msb(0); if (pit_expect_msb(0xff, &tsc, &d1)) { for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) { if (!pit_expect_msb(0xff-i, &delta, &d2)) break; delta -= tsc; /* * Extrapolate the error and fail fast if the error will * never be below 500 ppm. */ if (i == 1 && d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11) return 0; /* * Iterate until the error is less than 500 ppm */ if (d1+d2 >= delta >> 11) continue; /* * Check the PIT one more time to verify that * all TSC reads were stable wrt the PIT. * * This also guarantees serialization of the * last cycle read ('d2') in pit_expect_msb. */ if (!pit_verify_msb(0xfe - i)) break; goto success; } } pr_info("Fast TSC calibration failed\n"); return 0; success: /* * Ok, if we get here, then we've seen the * MSB of the PIT decrement 'i' times, and the * error has shrunk to less than 500 ppm. * * As a result, we can depend on there not being * any odd delays anywhere, and the TSC reads are * reliable (within the error). * * kHz = ticks / time-in-seconds / 1000; * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000) */ delta *= PIT_TICK_RATE; do_div(delta, i*256*1000); pr_info("Fast TSC calibration using PIT\n"); return delta; } /** * native_calibrate_tsc - determine TSC frequency * Determine TSC frequency via CPUID, else return 0. */ unsigned long native_calibrate_tsc(void) { unsigned int eax_denominator, ebx_numerator, ecx_hz, edx; unsigned int crystal_khz; if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; if (boot_cpu_data.cpuid_level < 0x15) return 0; eax_denominator = ebx_numerator = ecx_hz = edx = 0; /* CPUID 15H TSC/Crystal ratio, plus optionally Crystal Hz */ cpuid(0x15, &eax_denominator, &ebx_numerator, &ecx_hz, &edx); if (ebx_numerator == 0 || eax_denominator == 0) return 0; crystal_khz = ecx_hz / 1000; /* * Denverton SoCs don't report crystal clock, and also don't support * CPUID.0x16 for the calculation below, so hardcode the 25MHz crystal * clock. */ if (crystal_khz == 0 && boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT_D) crystal_khz = 25000; /* * TSC frequency reported directly by CPUID is a "hardware reported" * frequency and is the most accurate one so far we have. This * is considered a known frequency. */ if (crystal_khz != 0) setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); /* * Some Intel SoCs like Skylake and Kabylake don't report the crystal * clock, but we can easily calculate it to a high degree of accuracy * by considering the crystal ratio and the CPU speed. */ if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= 0x16) { unsigned int eax_base_mhz, ebx, ecx, edx; cpuid(0x16, &eax_base_mhz, &ebx, &ecx, &edx); crystal_khz = eax_base_mhz * 1000 * eax_denominator / ebx_numerator; } if (crystal_khz == 0) return 0; /* * For Atom SoCs TSC is the only reliable clocksource. * Mark TSC reliable so no watchdog on it. */ if (boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT) setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); #ifdef CONFIG_X86_LOCAL_APIC /* * The local APIC appears to be fed by the core crystal clock * (which sounds entirely sensible). We can set the global * lapic_timer_period here to avoid having to calibrate the APIC * timer later. */ lapic_timer_period = crystal_khz * 1000 / HZ; #endif return crystal_khz * ebx_numerator / eax_denominator; } static unsigned long cpu_khz_from_cpuid(void) { unsigned int eax_base_mhz, ebx_max_mhz, ecx_bus_mhz, edx; if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; if (boot_cpu_data.cpuid_level < 0x16) return 0; eax_base_mhz = ebx_max_mhz = ecx_bus_mhz = edx = 0; cpuid(0x16, &eax_base_mhz, &ebx_max_mhz, &ecx_bus_mhz, &edx); return eax_base_mhz * 1000; } /* * calibrate cpu using pit, hpet, and ptimer methods. They are available * later in boot after acpi is initialized. */ static unsigned long pit_hpet_ptimer_calibrate_cpu(void) { u64 tsc1, tsc2, delta, ref1, ref2; unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX; unsigned long flags, latch, ms; int hpet = is_hpet_enabled(), i, loopmin; /* * Run 5 calibration loops to get the lowest frequency value * (the best estimate). We use two different calibration modes * here: * * 1) PIT loop. We set the PIT Channel 2 to oneshot mode and * load a timeout of 50ms. We read the time right after we * started the timer and wait until the PIT count down reaches * zero. In each wait loop iteration we read the TSC and check * the delta to the previous read. We keep track of the min * and max values of that delta. The delta is mostly defined * by the IO time of the PIT access, so we can detect when * any disturbance happened between the two reads. If the * maximum time is significantly larger than the minimum time, * then we discard the result and have another try. * * 2) Reference counter. If available we use the HPET or the * PMTIMER as a reference to check the sanity of that value. * We use separate TSC readouts and check inside of the * reference read for any possible disturbance. We discard * disturbed values here as well. We do that around the PIT * calibration delay loop as we have to wait for a certain * amount of time anyway. */ /* Preset PIT loop values */ latch = CAL_LATCH; ms = CAL_MS; loopmin = CAL_PIT_LOOPS; for (i = 0; i < 3; i++) { unsigned long tsc_pit_khz; /* * Read the start value and the reference count of * hpet/pmtimer when available. Then do the PIT * calibration, which will take at least 50ms, and * read the end value. */ local_irq_save(flags); tsc1 = tsc_read_refs(&ref1, hpet); tsc_pit_khz = pit_calibrate_tsc(latch, ms, loopmin); tsc2 = tsc_read_refs(&ref2, hpet); local_irq_restore(flags); /* Pick the lowest PIT TSC calibration so far */ tsc_pit_min = min(tsc_pit_min, tsc_pit_khz); /* hpet or pmtimer available ? */ if (ref1 == ref2) continue; /* Check, whether the sampling was disturbed */ if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX) continue; tsc2 = (tsc2 - tsc1) * 1000000LL; if (hpet) tsc2 = calc_hpet_ref(tsc2, ref1, ref2); else tsc2 = calc_pmtimer_ref(tsc2, ref1, ref2); tsc_ref_min = min(tsc_ref_min, (unsigned long) tsc2); /* Check the reference deviation */ delta = ((u64) tsc_pit_min) * 100; do_div(delta, tsc_ref_min); /* * If both calibration results are inside a 10% window * then we can be sure, that the calibration * succeeded. We break out of the loop right away. We * use the reference value, as it is more precise. */ if (delta >= 90 && delta <= 110) { pr_info("PIT calibration matches %s. %d loops\n", hpet ? "HPET" : "PMTIMER", i + 1); return tsc_ref_min; } /* * Check whether PIT failed more than once. This * happens in virtualized environments. We need to * give the virtual PC a slightly longer timeframe for * the HPET/PMTIMER to make the result precise. */ if (i == 1 && tsc_pit_min == ULONG_MAX) { latch = CAL2_LATCH; ms = CAL2_MS; loopmin = CAL2_PIT_LOOPS; } } /* * Now check the results. */ if (tsc_pit_min == ULONG_MAX) { /* PIT gave no useful value */ pr_warn("Unable to calibrate against PIT\n"); /* We don't have an alternative source, disable TSC */ if (!hpet && !ref1 && !ref2) { pr_notice("No reference (HPET/PMTIMER) available\n"); return 0; } /* The alternative source failed as well, disable TSC */ if (tsc_ref_min == ULONG_MAX) { pr_warn("HPET/PMTIMER calibration failed\n"); return 0; } /* Use the alternative source */ pr_info("using %s reference calibration\n", hpet ? "HPET" : "PMTIMER"); return tsc_ref_min; } /* We don't have an alternative source, use the PIT calibration value */ if (!hpet && !ref1 && !ref2) { pr_info("Using PIT calibration value\n"); return tsc_pit_min; } /* The alternative source failed, use the PIT calibration value */ if (tsc_ref_min == ULONG_MAX) { pr_warn("HPET/PMTIMER calibration failed. Using PIT calibration.\n"); return tsc_pit_min; } /* * The calibration values differ too much. In doubt, we use * the PIT value as we know that there are PMTIMERs around * running at double speed. At least we let the user know: */ pr_warn("PIT calibration deviates from %s: %lu %lu\n", hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min); pr_info("Using PIT calibration value\n"); return tsc_pit_min; } /** * native_calibrate_cpu_early - can calibrate the cpu early in boot */ unsigned long native_calibrate_cpu_early(void) { unsigned long flags, fast_calibrate = cpu_khz_from_cpuid(); if (!fast_calibrate) fast_calibrate = cpu_khz_from_msr(); if (!fast_calibrate) { local_irq_save(flags); fast_calibrate = quick_pit_calibrate(); local_irq_restore(flags); } return fast_calibrate; } /** * native_calibrate_cpu - calibrate the cpu */ static unsigned long native_calibrate_cpu(void) { unsigned long tsc_freq = native_calibrate_cpu_early(); if (!tsc_freq) tsc_freq = pit_hpet_ptimer_calibrate_cpu(); return tsc_freq; } void recalibrate_cpu_khz(void) { #ifndef CONFIG_SMP unsigned long cpu_khz_old = cpu_khz; if (!boot_cpu_has(X86_FEATURE_TSC)) return; cpu_khz = x86_platform.calibrate_cpu(); tsc_khz = x86_platform.calibrate_tsc(); if (tsc_khz == 0) tsc_khz = cpu_khz; else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz) cpu_khz = tsc_khz; cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy, cpu_khz_old, cpu_khz); #endif } EXPORT_SYMBOL_GPL(recalibrate_cpu_khz); static unsigned long long cyc2ns_suspend; void tsc_save_sched_clock_state(void) { if (!sched_clock_stable()) return; cyc2ns_suspend = sched_clock(); } /* * Even on processors with invariant TSC, TSC gets reset in some the * ACPI system sleep states. And in some systems BIOS seem to reinit TSC to * arbitrary value (still sync'd across cpu's) during resume from such sleep * states. To cope up with this, recompute the cyc2ns_offset for each cpu so * that sched_clock() continues from the point where it was left off during * suspend. */ void tsc_restore_sched_clock_state(void) { unsigned long long offset; unsigned long flags; int cpu; if (!sched_clock_stable()) return; local_irq_save(flags); /* * We're coming out of suspend, there's no concurrency yet; don't * bother being nice about the RCU stuff, just write to both * data fields. */ this_cpu_write(cyc2ns.data[0].cyc2ns_offset, 0); this_cpu_write(cyc2ns.data[1].cyc2ns_offset, 0); offset = cyc2ns_suspend - sched_clock(); for_each_possible_cpu(cpu) { per_cpu(cyc2ns.data[0].cyc2ns_offset, cpu) = offset; per_cpu(cyc2ns.data[1].cyc2ns_offset, cpu) = offset; } local_irq_restore(flags); } #ifdef CONFIG_CPU_FREQ /* * Frequency scaling support. Adjust the TSC based timer when the CPU frequency * changes. * * NOTE: On SMP the situation is not fixable in general, so simply mark the TSC * as unstable and give up in those cases. * * Should fix up last_tsc too. Currently gettimeofday in the * first tick after the change will be slightly wrong. */ static unsigned int ref_freq; static unsigned long loops_per_jiffy_ref; static unsigned long tsc_khz_ref; static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { struct cpufreq_freqs *freq = data; if (num_online_cpus() > 1) { mark_tsc_unstable("cpufreq changes on SMP"); return 0; } if (!ref_freq) { ref_freq = freq->old; loops_per_jiffy_ref = boot_cpu_data.loops_per_jiffy; tsc_khz_ref = tsc_khz; } if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) { boot_cpu_data.loops_per_jiffy = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new); tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); if (!(freq->flags & CPUFREQ_CONST_LOOPS)) mark_tsc_unstable("cpufreq changes"); set_cyc2ns_scale(tsc_khz, freq->policy->cpu, rdtsc()); } return 0; } static struct notifier_block time_cpufreq_notifier_block = { .notifier_call = time_cpufreq_notifier }; static int __init cpufreq_register_tsc_scaling(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return 0; if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; cpufreq_register_notifier(&time_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); return 0; } core_initcall(cpufreq_register_tsc_scaling); #endif /* CONFIG_CPU_FREQ */ #define ART_CPUID_LEAF (0x15) #define ART_MIN_DENOMINATOR (1) /* * If ART is present detect the numerator:denominator to convert to TSC */ static void __init detect_art(void) { unsigned int unused; if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF) return; /* * Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required, * and the TSC counter resets must not occur asynchronously. */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR) || !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) || !boot_cpu_has(X86_FEATURE_TSC_ADJUST) || tsc_async_resets) return; cpuid(ART_CPUID_LEAF, &art_base_clk.denominator, &art_base_clk.numerator, &art_base_clk.freq_khz, &unused); art_base_clk.freq_khz /= KHZ; if (art_base_clk.denominator < ART_MIN_DENOMINATOR) return; rdmsrl(MSR_IA32_TSC_ADJUST, art_base_clk.offset); /* Make this sticky over multiple CPU init calls */ setup_force_cpu_cap(X86_FEATURE_ART); } /* clocksource code */ static void tsc_resume(struct clocksource *cs) { tsc_verify_tsc_adjust(true); } /* * We used to compare the TSC to the cycle_last value in the clocksource * structure to avoid a nasty time-warp. This can be observed in a * very small window right after one CPU updated cycle_last under * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which * is smaller than the cycle_last reference value due to a TSC which * is slightly behind. This delta is nowhere else observable, but in * that case it results in a forward time jump in the range of hours * due to the unsigned delta calculation of the time keeping core * code, which is necessary to support wrapping clocksources like pm * timer. * * This sanity check is now done in the core timekeeping code. * checking the result of read_tsc() - cycle_last for being negative. * That works because CLOCKSOURCE_MASK(64) does not mask out any bit. */ static u64 read_tsc(struct clocksource *cs) { return (u64)rdtsc_ordered(); } static void tsc_cs_mark_unstable(struct clocksource *cs) { if (tsc_unstable) return; tsc_unstable = 1; if (using_native_sched_clock()) clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to clocksource watchdog\n"); } static void tsc_cs_tick_stable(struct clocksource *cs) { if (tsc_unstable) return; if (using_native_sched_clock()) sched_clock_tick_stable(); } static int tsc_cs_enable(struct clocksource *cs) { vclocks_set_used(VDSO_CLOCKMODE_TSC); return 0; } /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ static struct clocksource clocksource_tsc_early = { .name = "tsc-early", .rating = 299, .uncertainty_margin = 32 * NSEC_PER_MSEC, .read = read_tsc, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, .id = CSID_X86_TSC_EARLY, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, .list = LIST_HEAD_INIT(clocksource_tsc_early.list), }; /* * Must mark VALID_FOR_HRES early such that when we unregister tsc_early * this one will immediately take over. We will only register if TSC has * been found good. */ static struct clocksource clocksource_tsc = { .name = "tsc", .rating = 300, .read = read_tsc, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_MUST_VERIFY | CLOCK_SOURCE_VERIFY_PERCPU, .id = CSID_X86_TSC, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, .list = LIST_HEAD_INIT(clocksource_tsc.list), }; void mark_tsc_unstable(char *reason) { if (tsc_unstable) return; tsc_unstable = 1; if (using_native_sched_clock()) clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to %s\n", reason); clocksource_mark_unstable(&clocksource_tsc_early); clocksource_mark_unstable(&clocksource_tsc); } EXPORT_SYMBOL_GPL(mark_tsc_unstable); static void __init tsc_disable_clocksource_watchdog(void) { clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; } bool tsc_clocksource_watchdog_disabled(void) { return !(clocksource_tsc.flags & CLOCK_SOURCE_MUST_VERIFY) && tsc_as_watchdog && !no_tsc_watchdog; } static void __init check_system_tsc_reliable(void) { #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) if (is_geode_lx()) { /* RTSC counts during suspend */ #define RTSC_SUSP 0x100 unsigned long res_low, res_high; rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); /* Geode_LX - the OLPC CPU has a very reliable TSC */ if (res_low & RTSC_SUSP) tsc_clocksource_reliable = 1; } #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; /* * Disable the clocksource watchdog when the system has: * - TSC running at constant frequency * - TSC which does not stop in C-States * - the TSC_ADJUST register which allows to detect even minimal * modifications * - not more than two sockets. As the number of sockets cannot be * evaluated at the early boot stage where this has to be * invoked, check the number of online memory nodes as a * fallback solution which is an reasonable estimate. */ if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && boot_cpu_has(X86_FEATURE_TSC_ADJUST) && nr_online_nodes <= 4) tsc_disable_clocksource_watchdog(); } /* * Make an educated guess if the TSC is trustworthy and synchronized * over all CPUs. */ int unsynchronized_tsc(void) { if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_unstable) return 1; #ifdef CONFIG_SMP if (apic_is_clustered_box()) return 1; #endif if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; if (tsc_clocksource_reliable) return 0; /* * Intel systems are normally all synchronized. * Exceptions must mark TSC as unstable: */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { /* assume multi socket systems are not synchronized: */ if (num_possible_cpus() > 1) return 1; } return 0; } static void tsc_refine_calibration_work(struct work_struct *work); static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); /** * tsc_refine_calibration_work - Further refine tsc freq calibration * @work: ignored. * * This functions uses delayed work over a period of a * second to further refine the TSC freq value. Since this is * timer based, instead of loop based, we don't block the boot * process while this longer calibration is done. * * If there are any calibration anomalies (too many SMIs, etc), * or the refined calibration is off by 1% of the fast early * calibration, we throw out the new calibration and use the * early calibration. */ static void tsc_refine_calibration_work(struct work_struct *work) { static u64 tsc_start = ULLONG_MAX, ref_start; static int hpet; u64 tsc_stop, ref_stop, delta; unsigned long freq; int cpu; /* Don't bother refining TSC on unstable systems */ if (tsc_unstable) goto unreg; /* * Since the work is started early in boot, we may be * delayed the first time we expire. So set the workqueue * again once we know timers are working. */ if (tsc_start == ULLONG_MAX) { restart: /* * Only set hpet once, to avoid mixing hardware * if the hpet becomes enabled later. */ hpet = is_hpet_enabled(); tsc_start = tsc_read_refs(&ref_start, hpet); schedule_delayed_work(&tsc_irqwork, HZ); return; } tsc_stop = tsc_read_refs(&ref_stop, hpet); /* hpet or pmtimer available ? */ if (ref_start == ref_stop) goto out; /* Check, whether the sampling was disturbed */ if (tsc_stop == ULLONG_MAX) goto restart; delta = tsc_stop - tsc_start; delta *= 1000000LL; if (hpet) freq = calc_hpet_ref(delta, ref_start, ref_stop); else freq = calc_pmtimer_ref(delta, ref_start, ref_stop); /* Will hit this only if tsc_force_recalibrate has been set */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { /* Warn if the deviation exceeds 500 ppm */ if (abs(tsc_khz - freq) > (tsc_khz >> 11)) { pr_warn("Warning: TSC freq calibrated by CPUID/MSR differs from what is calibrated by HW timer, please check with vendor!!\n"); pr_info("Previous calibrated TSC freq:\t %lu.%03lu MHz\n", (unsigned long)tsc_khz / 1000, (unsigned long)tsc_khz % 1000); } pr_info("TSC freq recalibrated by [%s]:\t %lu.%03lu MHz\n", hpet ? "HPET" : "PM_TIMER", (unsigned long)freq / 1000, (unsigned long)freq % 1000); return; } /* Make sure we're within 1% */ if (abs(tsc_khz - freq) > tsc_khz/100) goto out; tsc_khz = freq; pr_info("Refined TSC clocksource calibration: %lu.%03lu MHz\n", (unsigned long)tsc_khz / 1000, (unsigned long)tsc_khz % 1000); /* Inform the TSC deadline clockevent devices about the recalibration */ lapic_update_tsc_freq(); /* Update the sched_clock() rate to match the clocksource one */ for_each_possible_cpu(cpu) set_cyc2ns_scale(tsc_khz, cpu, tsc_stop); out: if (tsc_unstable) goto unreg; if (boot_cpu_has(X86_FEATURE_ART)) { have_art = true; clocksource_tsc.base = &art_base_clk; } clocksource_register_khz(&clocksource_tsc, tsc_khz); unreg: clocksource_unregister(&clocksource_tsc_early); } static int __init init_tsc_clocksource(void) { if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz) return 0; if (tsc_unstable) { clocksource_unregister(&clocksource_tsc_early); return 0; } if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; /* * When TSC frequency is known (retrieved via MSR or CPUID), we skip * the refined calibration and directly register it as a clocksource. */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { if (boot_cpu_has(X86_FEATURE_ART)) { have_art = true; clocksource_tsc.base = &art_base_clk; } clocksource_register_khz(&clocksource_tsc, tsc_khz); clocksource_unregister(&clocksource_tsc_early); if (!tsc_force_recalibrate) return 0; } schedule_delayed_work(&tsc_irqwork, 0); return 0; } /* * We use device_initcall here, to ensure we run after the hpet * is fully initialized, which may occur at fs_initcall time. */ device_initcall(init_tsc_clocksource); static bool __init determine_cpu_tsc_frequencies(bool early) { /* Make sure that cpu and tsc are not already calibrated */ WARN_ON(cpu_khz || tsc_khz); if (early) { cpu_khz = x86_platform.calibrate_cpu(); if (tsc_early_khz) { tsc_khz = tsc_early_khz; } else { tsc_khz = x86_platform.calibrate_tsc(); clocksource_tsc.freq_khz = tsc_khz; } } else { /* We should not be here with non-native cpu calibration */ WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu); cpu_khz = pit_hpet_ptimer_calibrate_cpu(); } /* * Trust non-zero tsc_khz as authoritative, * and use it to sanity check cpu_khz, * which will be off if system timer is off. */ if (tsc_khz == 0) tsc_khz = cpu_khz; else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz) cpu_khz = tsc_khz; if (tsc_khz == 0) return false; pr_info("Detected %lu.%03lu MHz processor\n", (unsigned long)cpu_khz / KHZ, (unsigned long)cpu_khz % KHZ); if (cpu_khz != tsc_khz) { pr_info("Detected %lu.%03lu MHz TSC", (unsigned long)tsc_khz / KHZ, (unsigned long)tsc_khz % KHZ); } return true; } static unsigned long __init get_loops_per_jiffy(void) { u64 lpj = (u64)tsc_khz * KHZ; do_div(lpj, HZ); return lpj; } static void __init tsc_enable_sched_clock(void) { loops_per_jiffy = get_loops_per_jiffy(); use_tsc_delay(); /* Sanitize TSC ADJUST before cyc2ns gets initialized */ tsc_store_and_check_tsc_adjust(true); cyc2ns_init_boot_cpu(); static_branch_enable(&__use_tsc); } void __init tsc_early_init(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return; /* Don't change UV TSC multi-chassis synchronization */ if (is_early_uv_system()) return; if (!determine_cpu_tsc_frequencies(true)) return; tsc_enable_sched_clock(); } void __init tsc_init(void) { if (!cpu_feature_enabled(X86_FEATURE_TSC)) { setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } /* * native_calibrate_cpu_early can only calibrate using methods that are * available early in boot. */ if (x86_platform.calibrate_cpu == native_calibrate_cpu_early) x86_platform.calibrate_cpu = native_calibrate_cpu; if (!tsc_khz) { /* We failed to determine frequencies earlier, try again */ if (!determine_cpu_tsc_frequencies(false)) { mark_tsc_unstable("could not calculate TSC khz"); setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } tsc_enable_sched_clock(); } cyc2ns_init_secondary_cpus(); if (!no_sched_irq_time) enable_sched_clock_irqtime(); lpj_fine = get_loops_per_jiffy(); check_system_tsc_reliable(); if (unsynchronized_tsc()) { mark_tsc_unstable("TSCs unsynchronized"); return; } if (tsc_clocksource_reliable || no_tsc_watchdog) tsc_disable_clocksource_watchdog(); clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); } #ifdef CONFIG_SMP /* * Check whether existing calibration data can be reused. */ unsigned long calibrate_delay_is_known(void) { int sibling, cpu = smp_processor_id(); int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC); const struct cpumask *mask = topology_core_cpumask(cpu); /* * If TSC has constant frequency and TSC is synchronized across * sockets then reuse CPU0 calibration. */ if (constant_tsc && !tsc_unstable) return cpu_data(0).loops_per_jiffy; /* * If TSC has constant frequency and TSC is not synchronized across * sockets and this is not the first CPU in the socket, then reuse * the calibration value of an already online CPU on that socket. * * This assumes that CONSTANT_TSC is consistent for all CPUs in a * socket. */ if (!constant_tsc || !mask) return 0; sibling = cpumask_any_but(mask, cpu); if (sibling < nr_cpu_ids) return cpu_data(sibling).loops_per_jiffy; return 0; } #endif |
| 3 3 7 108 6 42 1 31 14 3 33 41 17 14 32 82 81 81 1 20 15 50 41 50 41 73 16 79 2 20 52 52 4 48 3 5 10 48 5 5 48 6 12 86 17 87 171 102 97 42 40 64 45 103 1 92 11 23 3 26 15 14 2 24 6 30 64 5 16 4 12 1 16 1 1 12 4 8 69 41 155 22 97 91 24 21 75 44 175 149 63 167 20 175 21 40 2 49 2 1 46 1 40 32 40 13 4 41 1 1 42 12 36 37 36 3 2 1 1 1 1 1 2 69 2 68 68 16 10 3 3 8 4 1 1 3 46 45 1 1 1 17 3 10 1 2 2 11 10 7 4 7 4 10 11 11 11 2 9 9 1 1 7 6 5 5 5 3 3 5 3 3 3 9 4 6 1 2 7 4 1 2 6 6 1 5 11 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * * TODO: Merge attr_set_size/attr_data_get_block/attr_allocate_frame? */ #include <linux/fs.h> #include <linux/slab.h> #include <linux/kernel.h> #include "debug.h" #include "ntfs.h" #include "ntfs_fs.h" /* * You can set external NTFS_MIN_LOG2_OF_CLUMP/NTFS_MAX_LOG2_OF_CLUMP to manage * preallocate algorithm. */ #ifndef NTFS_MIN_LOG2_OF_CLUMP #define NTFS_MIN_LOG2_OF_CLUMP 16 #endif #ifndef NTFS_MAX_LOG2_OF_CLUMP #define NTFS_MAX_LOG2_OF_CLUMP 26 #endif // 16M #define NTFS_CLUMP_MIN (1 << (NTFS_MIN_LOG2_OF_CLUMP + 8)) // 16G #define NTFS_CLUMP_MAX (1ull << (NTFS_MAX_LOG2_OF_CLUMP + 8)) static inline u64 get_pre_allocated(u64 size) { u32 clump; u8 align_shift; u64 ret; if (size <= NTFS_CLUMP_MIN) { clump = 1 << NTFS_MIN_LOG2_OF_CLUMP; align_shift = NTFS_MIN_LOG2_OF_CLUMP; } else if (size >= NTFS_CLUMP_MAX) { clump = 1 << NTFS_MAX_LOG2_OF_CLUMP; align_shift = NTFS_MAX_LOG2_OF_CLUMP; } else { align_shift = NTFS_MIN_LOG2_OF_CLUMP - 1 + __ffs(size >> (8 + NTFS_MIN_LOG2_OF_CLUMP)); clump = 1u << align_shift; } ret = (((size + clump - 1) >> align_shift)) << align_shift; return ret; } /* * attr_load_runs - Load all runs stored in @attr. */ static int attr_load_runs(struct ATTRIB *attr, struct ntfs_inode *ni, struct runs_tree *run, const CLST *vcn) { int err; CLST svcn = le64_to_cpu(attr->nres.svcn); CLST evcn = le64_to_cpu(attr->nres.evcn); u32 asize; u16 run_off; if (svcn >= evcn + 1 || run_is_mapped_full(run, svcn, evcn)) return 0; if (vcn && (evcn < *vcn || *vcn < svcn)) return -EINVAL; asize = le32_to_cpu(attr->size); run_off = le16_to_cpu(attr->nres.run_off); if (run_off > asize) return -EINVAL; err = run_unpack_ex(run, ni->mi.sbi, ni->mi.rno, svcn, evcn, vcn ? *vcn : svcn, Add2Ptr(attr, run_off), asize - run_off); if (err < 0) return err; return 0; } /* * run_deallocate_ex - Deallocate clusters. */ static int run_deallocate_ex(struct ntfs_sb_info *sbi, struct runs_tree *run, CLST vcn, CLST len, CLST *done, bool trim) { int err = 0; CLST vcn_next, vcn0 = vcn, lcn, clen, dn = 0; size_t idx; if (!len) goto out; if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) { failed: run_truncate(run, vcn0); err = -EINVAL; goto out; } for (;;) { if (clen > len) clen = len; if (!clen) { err = -EINVAL; goto out; } if (lcn != SPARSE_LCN) { if (sbi) { /* mark bitmap range [lcn + clen) as free and trim clusters. */ mark_as_free_ex(sbi, lcn, clen, trim); } dn += clen; } len -= clen; if (!len) break; vcn_next = vcn + clen; if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || vcn != vcn_next) { /* Save memory - don't load entire run. */ goto failed; } } out: if (done) *done += dn; return err; } /* * attr_allocate_clusters - Find free space, mark it as used and store in @run. */ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, CLST *new_lcn, CLST *new_len) { int err; CLST flen, vcn0 = vcn, pre = pre_alloc ? *pre_alloc : 0; size_t cnt = run->count; for (;;) { err = ntfs_look_for_free_space(sbi, lcn, len + pre, &lcn, &flen, opt); if (err == -ENOSPC && pre) { pre = 0; if (*pre_alloc) *pre_alloc = 0; continue; } if (err) goto out; if (vcn == vcn0) { /* Return the first fragment. */ if (new_lcn) *new_lcn = lcn; if (new_len) *new_len = flen; } /* Add new fragment into run storage. */ if (!run_add_entry(run, vcn, lcn, flen, opt & ALLOCATE_MFT)) { /* Undo last 'ntfs_look_for_free_space' */ mark_as_free_ex(sbi, lcn, len, false); err = -ENOMEM; goto out; } if (opt & ALLOCATE_ZERO) { u8 shift = sbi->cluster_bits - SECTOR_SHIFT; err = blkdev_issue_zeroout(sbi->sb->s_bdev, (sector_t)lcn << shift, (sector_t)flen << shift, GFP_NOFS, 0); if (err) goto out; } vcn += flen; if (flen >= len || (opt & ALLOCATE_MFT) || (fr && run->count - cnt >= fr)) { *alen = vcn - vcn0; return 0; } len -= flen; } out: /* Undo 'ntfs_look_for_free_space' */ if (vcn - vcn0) { run_deallocate_ex(sbi, run, vcn0, vcn - vcn0, NULL, false); run_truncate(run, vcn0); } return err; } /* * attr_make_nonresident * * If page is not NULL - it is already contains resident data * and locked (called from ni_write_frame()). */ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, struct ATTR_LIST_ENTRY *le, struct mft_inode *mi, u64 new_size, struct runs_tree *run, struct ATTRIB **ins_attr, struct page *page) { struct ntfs_sb_info *sbi; struct ATTRIB *attr_s; struct MFT_REC *rec; u32 used, asize, rsize, aoff; bool is_data; CLST len, alen; char *next; int err; if (attr->non_res) { *ins_attr = attr; return 0; } sbi = mi->sbi; rec = mi->mrec; attr_s = NULL; used = le32_to_cpu(rec->used); asize = le32_to_cpu(attr->size); next = Add2Ptr(attr, asize); aoff = PtrOffset(rec, attr); rsize = le32_to_cpu(attr->res.data_size); is_data = attr->type == ATTR_DATA && !attr->name_len; /* len - how many clusters required to store 'rsize' bytes */ if (is_attr_compressed(attr)) { u8 shift = sbi->cluster_bits + NTFS_LZNT_CUNIT; len = ((rsize + (1u << shift) - 1) >> shift) << NTFS_LZNT_CUNIT; } else { len = bytes_to_cluster(sbi, rsize); } run_init(run); /* Make a copy of original attribute. */ attr_s = kmemdup(attr, asize, GFP_NOFS); if (!attr_s) { err = -ENOMEM; goto out; } if (!len) { /* Empty resident -> Empty nonresident. */ alen = 0; } else { const char *data = resident_data(attr); err = attr_allocate_clusters(sbi, run, 0, 0, len, NULL, ALLOCATE_DEF, &alen, 0, NULL, NULL); if (err) goto out1; if (!rsize) { /* Empty resident -> Non empty nonresident. */ } else if (!is_data) { err = ntfs_sb_write_run(sbi, run, 0, data, rsize, 0); if (err) goto out2; } else if (!page) { struct address_space *mapping = ni->vfs_inode.i_mapping; struct folio *folio; folio = __filemap_get_folio( mapping, 0, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) { err = PTR_ERR(folio); goto out2; } folio_fill_tail(folio, 0, data, rsize); folio_mark_uptodate(folio); folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); } } /* Remove original attribute. */ used -= asize; memmove(attr, Add2Ptr(attr, asize), used - aoff); rec->used = cpu_to_le32(used); mi->dirty = true; if (le) al_remove_le(ni, le); err = ni_insert_nonresident(ni, attr_s->type, attr_name(attr_s), attr_s->name_len, run, 0, alen, attr_s->flags, &attr, NULL, NULL); if (err) goto out3; kfree(attr_s); attr->nres.data_size = cpu_to_le64(rsize); attr->nres.valid_size = attr->nres.data_size; *ins_attr = attr; if (is_data) ni->ni_flags &= ~NI_FLAG_RESIDENT; /* Resident attribute becomes non resident. */ return 0; out3: attr = Add2Ptr(rec, aoff); memmove(next, attr, used - aoff); memcpy(attr, attr_s, asize); rec->used = cpu_to_le32(used + asize); mi->dirty = true; out2: /* Undo: do not trim new allocated clusters. */ run_deallocate(sbi, run, false); run_close(run); out1: kfree(attr_s); out: return err; } /* * attr_set_size_res - Helper for attr_set_size(). */ static int attr_set_size_res(struct ntfs_inode *ni, struct ATTRIB *attr, struct ATTR_LIST_ENTRY *le, struct mft_inode *mi, u64 new_size, struct runs_tree *run, struct ATTRIB **ins_attr) { struct ntfs_sb_info *sbi = mi->sbi; struct MFT_REC *rec = mi->mrec; u32 used = le32_to_cpu(rec->used); u32 asize = le32_to_cpu(attr->size); u32 aoff = PtrOffset(rec, attr); u32 rsize = le32_to_cpu(attr->res.data_size); u32 tail = used - aoff - asize; char *next = Add2Ptr(attr, asize); s64 dsize = ALIGN(new_size, 8) - ALIGN(rsize, 8); if (dsize < 0) { memmove(next + dsize, next, tail); } else if (dsize > 0) { if (used + dsize > sbi->max_bytes_per_attr) return attr_make_nonresident(ni, attr, le, mi, new_size, run, ins_attr, NULL); memmove(next + dsize, next, tail); memset(next, 0, dsize); } if (new_size > rsize) memset(Add2Ptr(resident_data(attr), rsize), 0, new_size - rsize); rec->used = cpu_to_le32(used + dsize); attr->size = cpu_to_le32(asize + dsize); attr->res.data_size = cpu_to_le32(new_size); mi->dirty = true; *ins_attr = attr; return 0; } /* * attr_set_size - Change the size of attribute. * * Extend: * - Sparse/compressed: No allocated clusters. * - Normal: Append allocated and preallocated new clusters. * Shrink: * - No deallocate if @keep_prealloc is set. */ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct runs_tree *run, u64 new_size, const u64 *new_valid, bool keep_prealloc, struct ATTRIB **ret) { int err = 0; struct ntfs_sb_info *sbi = ni->mi.sbi; u8 cluster_bits = sbi->cluster_bits; bool is_mft = ni->mi.rno == MFT_REC_MFT && type == ATTR_DATA && !name_len; u64 old_valid, old_size, old_alloc, new_alloc, new_alloc_tmp; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST alen, vcn, lcn, new_alen, old_alen, svcn, evcn; CLST next_svcn, pre_alloc = -1, done = 0; bool is_ext, is_bad = false; bool dirty = false; u32 align; struct MFT_REC *rec; again: alen = 0; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL, &mi_b); if (!attr_b) { err = -ENOENT; goto bad_inode; } if (!attr_b->non_res) { err = attr_set_size_res(ni, attr_b, le_b, mi_b, new_size, run, &attr_b); if (err) return err; /* Return if file is still resident. */ if (!attr_b->non_res) { dirty = true; goto ok1; } /* Layout of records may be changed, so do a full search. */ goto again; } is_ext = is_attr_ext(attr_b); align = sbi->cluster_size; if (is_ext) align <<= attr_b->nres.c_unit; old_valid = le64_to_cpu(attr_b->nres.valid_size); old_size = le64_to_cpu(attr_b->nres.data_size); old_alloc = le64_to_cpu(attr_b->nres.alloc_size); again_1: old_alen = old_alloc >> cluster_bits; new_alloc = (new_size + align - 1) & ~(u64)(align - 1); new_alen = new_alloc >> cluster_bits; if (keep_prealloc && new_size < old_size) { attr_b->nres.data_size = cpu_to_le64(new_size); mi_b->dirty = dirty = true; goto ok; } vcn = old_alen - 1; svcn = le64_to_cpu(attr_b->nres.svcn); evcn = le64_to_cpu(attr_b->nres.evcn); if (svcn <= vcn && vcn <= evcn) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, &vcn, &mi); if (!attr) { err = -EINVAL; goto bad_inode; } next_le_1: svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); } /* * Here we have: * attr,mi,le - last attribute segment (containing 'vcn'). * attr_b,mi_b,le_b - base (primary) attribute segment. */ next_le: rec = mi->mrec; err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; if (new_size > old_size) { CLST to_allocate; size_t free; if (new_alloc <= old_alloc) { attr_b->nres.data_size = cpu_to_le64(new_size); mi_b->dirty = dirty = true; goto ok; } /* * Add clusters. In simple case we have to: * - allocate space (vcn, lcn, len) * - update packed run in 'mi' * - update attr->nres.evcn * - update attr_b->nres.data_size/attr_b->nres.alloc_size */ to_allocate = new_alen - old_alen; add_alloc_in_same_attr_seg: lcn = 0; if (is_mft) { /* MFT allocates clusters from MFT zone. */ pre_alloc = 0; } else if (is_ext) { /* No preallocate for sparse/compress. */ pre_alloc = 0; } else if (pre_alloc == -1) { pre_alloc = 0; if (type == ATTR_DATA && !name_len && sbi->options->prealloc) { pre_alloc = bytes_to_cluster( sbi, get_pre_allocated( new_size)) - new_alen; } /* Get the last LCN to allocate from. */ if (old_alen && !run_lookup_entry(run, vcn, &lcn, NULL, NULL)) { lcn = SPARSE_LCN; } if (lcn == SPARSE_LCN) lcn = 0; else if (lcn) lcn += 1; free = wnd_zeroes(&sbi->used.bitmap); if (to_allocate > free) { err = -ENOSPC; goto out; } if (pre_alloc && to_allocate + pre_alloc > free) pre_alloc = 0; } vcn = old_alen; if (is_ext) { if (!run_add_entry(run, vcn, SPARSE_LCN, to_allocate, false)) { err = -ENOMEM; goto out; } alen = to_allocate; } else { /* ~3 bytes per fragment. */ err = attr_allocate_clusters( sbi, run, vcn, lcn, to_allocate, &pre_alloc, is_mft ? ALLOCATE_MFT : ALLOCATE_DEF, &alen, is_mft ? 0 : (sbi->record_size - le32_to_cpu(rec->used) + 8) / 3 + 1, NULL, NULL); if (err) goto out; } done += alen; vcn += alen; if (to_allocate > alen) to_allocate -= alen; else to_allocate = 0; pack_runs: err = mi_pack_runs(mi, attr, run, vcn - svcn); if (err) goto undo_1; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; new_alloc_tmp = (u64)next_svcn << cluster_bits; attr_b->nres.alloc_size = cpu_to_le64(new_alloc_tmp); mi_b->dirty = dirty = true; if (next_svcn >= vcn && !to_allocate) { /* Normal way. Update attribute and exit. */ attr_b->nres.data_size = cpu_to_le64(new_size); goto ok; } /* At least two MFT to avoid recursive loop. */ if (is_mft && next_svcn == vcn && ((u64)done << sbi->cluster_bits) >= 2 * sbi->record_size) { new_size = new_alloc_tmp; attr_b->nres.data_size = attr_b->nres.alloc_size; goto ok; } if (le32_to_cpu(rec->used) < sbi->record_size) { old_alen = next_svcn; evcn = old_alen - 1; goto add_alloc_in_same_attr_seg; } attr_b->nres.data_size = attr_b->nres.alloc_size; if (new_alloc_tmp < old_valid) attr_b->nres.valid_size = attr_b->nres.data_size; if (type == ATTR_LIST) { err = ni_expand_list(ni); if (err) goto undo_2; if (next_svcn < vcn) goto pack_runs; /* Layout of records is changed. */ goto again; } if (!ni->attr_list.size) { err = ni_create_attr_list(ni); /* In case of error layout of records is not changed. */ if (err) goto undo_2; /* Layout of records is changed. */ } if (next_svcn >= vcn) { /* This is MFT data, repeat. */ goto again; } /* Insert new attribute segment. */ err = ni_insert_nonresident(ni, type, name, name_len, run, next_svcn, vcn - next_svcn, attr_b->flags, &attr, &mi, NULL); /* * Layout of records maybe changed. * Find base attribute to update. */ le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, type, name, name_len, NULL, &mi_b); if (!attr_b) { err = -EINVAL; goto bad_inode; } if (err) { /* ni_insert_nonresident failed. */ attr = NULL; goto undo_2; } /* keep runs for $MFT::$ATTR_DATA and $MFT::$ATTR_BITMAP. */ if (ni->mi.rno != MFT_REC_MFT) run_truncate_head(run, evcn + 1); svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); /* * Attribute is in consistency state. * Save this point to restore to if next steps fail. */ old_valid = old_size = old_alloc = (u64)vcn << cluster_bits; attr_b->nres.valid_size = attr_b->nres.data_size = attr_b->nres.alloc_size = cpu_to_le64(old_size); mi_b->dirty = dirty = true; goto again_1; } if (new_size != old_size || (new_alloc != old_alloc && !keep_prealloc)) { /* * Truncate clusters. In simple case we have to: * - update packed run in 'mi' * - update attr->nres.evcn * - update attr_b->nres.data_size/attr_b->nres.alloc_size * - mark and trim clusters as free (vcn, lcn, len) */ CLST dlen = 0; vcn = max(svcn, new_alen); new_alloc_tmp = (u64)vcn << cluster_bits; if (vcn > svcn) { err = mi_pack_runs(mi, attr, run, vcn - svcn); if (err) goto out; } else if (le && le->vcn) { u16 le_sz = le16_to_cpu(le->size); /* * NOTE: List entries for one attribute are always * the same size. We deal with last entry (vcn==0) * and it is not first in entries array * (list entry for std attribute always first). * So it is safe to step back. */ mi_remove_attr(NULL, mi, attr); if (!al_remove_le(ni, le)) { err = -EINVAL; goto bad_inode; } le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz); } else { attr->nres.evcn = cpu_to_le64((u64)vcn - 1); mi->dirty = true; } attr_b->nres.alloc_size = cpu_to_le64(new_alloc_tmp); if (vcn == new_alen) { attr_b->nres.data_size = cpu_to_le64(new_size); if (new_size < old_valid) attr_b->nres.valid_size = attr_b->nres.data_size; } else { if (new_alloc_tmp <= le64_to_cpu(attr_b->nres.data_size)) attr_b->nres.data_size = attr_b->nres.alloc_size; if (new_alloc_tmp < le64_to_cpu(attr_b->nres.valid_size)) attr_b->nres.valid_size = attr_b->nres.alloc_size; } mi_b->dirty = dirty = true; err = run_deallocate_ex(sbi, run, vcn, evcn - vcn + 1, &dlen, true); if (err) goto out; if (is_ext) { /* dlen - really deallocated clusters. */ le64_sub_cpu(&attr_b->nres.total_size, ((u64)dlen << cluster_bits)); } run_truncate(run, vcn); if (new_alloc_tmp <= new_alloc) goto ok; old_size = new_alloc_tmp; vcn = svcn - 1; if (le == le_b) { attr = attr_b; mi = mi_b; evcn = svcn - 1; svcn = 0; goto next_le; } if (le->type != type || le->name_len != name_len || memcmp(le_name(le), name, name_len * sizeof(short))) { err = -EINVAL; goto bad_inode; } err = ni_load_mi(ni, le, &mi); if (err) goto out; attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id); if (!attr) { err = -EINVAL; goto bad_inode; } goto next_le_1; } ok: if (new_valid) { __le64 valid = cpu_to_le64(min(*new_valid, new_size)); if (attr_b->nres.valid_size != valid) { attr_b->nres.valid_size = valid; mi_b->dirty = true; } } ok1: if (ret) *ret = attr_b; if (((type == ATTR_DATA && !name_len) || (type == ATTR_ALLOC && name == I30_NAME))) { /* Update inode_set_bytes. */ if (attr_b->non_res) { new_alloc = le64_to_cpu(attr_b->nres.alloc_size); if (inode_get_bytes(&ni->vfs_inode) != new_alloc) { inode_set_bytes(&ni->vfs_inode, new_alloc); dirty = true; } } /* Don't forget to update duplicate information in parent. */ if (dirty) { ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mark_inode_dirty(&ni->vfs_inode); } } return 0; undo_2: vcn -= alen; attr_b->nres.data_size = cpu_to_le64(old_size); attr_b->nres.valid_size = cpu_to_le64(old_valid); attr_b->nres.alloc_size = cpu_to_le64(old_alloc); /* Restore 'attr' and 'mi'. */ if (attr) goto restore_run; if (le64_to_cpu(attr_b->nres.svcn) <= svcn && svcn <= le64_to_cpu(attr_b->nres.evcn)) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, type, name, name_len, &svcn, &mi); if (!attr) goto bad_inode; } restore_run: if (mi_pack_runs(mi, attr, run, evcn - svcn + 1)) is_bad = true; undo_1: run_deallocate_ex(sbi, run, vcn, alen, NULL, false); run_truncate(run, vcn); out: if (is_bad) { bad_inode: _ntfs_bad_inode(&ni->vfs_inode); } return err; } /* * attr_data_get_block - Returns 'lcn' and 'len' for given 'vcn'. * * @new == NULL means just to get current mapping for 'vcn' * @new != NULL means allocate real cluster if 'vcn' maps to hole * @zero - zeroout new allocated clusters * * NOTE: * - @new != NULL is called only for sparsed or compressed attributes. * - new allocated clusters are zeroed via blkdev_issue_zeroout. */ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, CLST *len, bool *new, bool zero) { int err = 0; struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi; u8 cluster_bits; struct ATTRIB *attr, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end, vcn0, alen; CLST alloc, evcn; unsigned fr; u64 total_size, total_size0; int step = 0; if (new) *new = false; /* Try to find in cache. */ down_read(&ni->file.run_lock); if (!run_lookup_entry(run, vcn, lcn, len, NULL)) *len = 0; up_read(&ni->file.run_lock); if (*len && (*lcn != SPARSE_LCN || !new)) return 0; /* Fast normal way without allocation. */ /* No cluster in cache or we need to allocate cluster in hole. */ sbi = ni->mi.sbi; cluster_bits = sbi->cluster_bits; ni_lock(ni); down_write(&ni->file.run_lock); /* Repeat the code above (under write lock). */ if (!run_lookup_entry(run, vcn, lcn, len, NULL)) *len = 0; if (*len) { if (*lcn != SPARSE_LCN || !new) goto out; /* normal way without allocation. */ if (clen > *len) clen = *len; } le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -ENOENT; goto out; } if (!attr_b->non_res) { *lcn = RESIDENT_LCN; *len = 1; goto out; } asize = le64_to_cpu(attr_b->nres.alloc_size) >> cluster_bits; if (vcn >= asize) { if (new) { err = -EINVAL; } else { *len = 1; *lcn = SPARSE_LCN; } goto out; } svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; attr = attr_b; le = le_b; mi = mi_b; if (le_b && (vcn < svcn || evcn1 <= vcn)) { attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } /* Load in cache actual information. */ err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; /* Check for compressed frame. */ err = attr_is_frame_compressed(ni, attr, vcn >> NTFS_LZNT_CUNIT, &hint); if (err) goto out; if (hint) { /* if frame is compressed - don't touch it. */ *lcn = COMPRESSED_LCN; *len = hint; err = -EOPNOTSUPP; goto out; } if (!*len) { if (run_lookup_entry(run, vcn, lcn, len, NULL)) { if (*lcn != SPARSE_LCN || !new) goto ok; /* Slow normal way without allocation. */ if (clen > *len) clen = *len; } else if (!new) { /* Here we may return -ENOENT. * In any case caller gets zero length. */ goto ok; } } if (!is_attr_ext(attr_b)) { /* The code below only for sparsed or compressed attributes. */ err = -EINVAL; goto out; } vcn0 = vcn; to_alloc = clen; fr = (sbi->record_size - le32_to_cpu(mi->mrec->used) + 8) / 3 + 1; /* Allocate frame aligned clusters. * ntfs.sys usually uses 16 clusters per frame for sparsed or compressed. * ntfs3 uses 1 cluster per frame for new created sparsed files. */ if (attr_b->nres.c_unit) { CLST clst_per_frame = 1u << attr_b->nres.c_unit; CLST cmask = ~(clst_per_frame - 1); /* Get frame aligned vcn and to_alloc. */ vcn = vcn0 & cmask; to_alloc = ((vcn0 + clen + clst_per_frame - 1) & cmask) - vcn; if (fr < clst_per_frame) fr = clst_per_frame; zero = true; /* Check if 'vcn' and 'vcn0' in different attribute segments. */ if (vcn < svcn || evcn1 <= vcn) { /* Load attribute for truncated vcn. */ attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; } } if (vcn + to_alloc > asize) to_alloc = asize - vcn; /* Get the last LCN to allocate from. */ hint = 0; if (vcn > evcn1) { if (!run_add_entry(run, evcn1, SPARSE_LCN, vcn - evcn1, false)) { err = -ENOMEM; goto out; } } else if (vcn && !run_lookup_entry(run, vcn - 1, &hint, NULL, NULL)) { hint = -1; } /* Allocate and zeroout new clusters. */ err = attr_allocate_clusters(sbi, run, vcn, hint + 1, to_alloc, NULL, zero ? ALLOCATE_ZERO : ALLOCATE_DEF, &alen, fr, lcn, len); if (err) goto out; *new = true; step = 1; end = vcn + alen; /* Save 'total_size0' to restore if error. */ total_size0 = le64_to_cpu(attr_b->nres.total_size); total_size = total_size0 + ((u64)alen << cluster_bits); if (vcn != vcn0) { if (!run_lookup_entry(run, vcn0, lcn, len, NULL)) { err = -EINVAL; goto out; } if (*lcn == SPARSE_LCN) { /* Internal error. Should not happened. */ WARN_ON(1); err = -EINVAL; goto out; } /* Check case when vcn0 + len overlaps new allocated clusters. */ if (vcn0 + *len > end) *len = end - vcn0; } repack: err = mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn); if (err) goto out; attr_b->nres.total_size = cpu_to_le64(total_size); inode_set_bytes(&ni->vfs_inode, total_size); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mi_b->dirty = true; mark_inode_dirty(&ni->vfs_inode); /* Stored [vcn : next_svcn) from [vcn : end). */ next_svcn = le64_to_cpu(attr->nres.evcn) + 1; if (end <= evcn1) { if (next_svcn == evcn1) { /* Normal way. Update attribute and exit. */ goto ok; } /* Add new segment [next_svcn : evcn1 - next_svcn). */ if (!ni->attr_list.size) { err = ni_create_attr_list(ni); if (err) goto undo1; /* Layout of records is changed. */ le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -ENOENT; goto out; } attr = attr_b; le = le_b; mi = mi_b; goto repack; } } /* * The code below may require additional cluster (to extend attribute list) * and / or one MFT record * It is too complex to undo operations if -ENOSPC occurs deep inside * in 'ni_insert_nonresident'. * Return in advance -ENOSPC here if there are no free cluster and no free MFT. */ if (!ntfs_check_for_free_space(sbi, 1, 1)) { /* Undo step 1. */ err = -ENOSPC; goto undo1; } step = 2; svcn = evcn1; /* Estimate next attribute. */ attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &svcn, &mi); if (!attr) { /* Insert new attribute segment. */ goto ins_ext; } /* Try to update existed attribute segment. */ alloc = bytes_to_cluster(sbi, le64_to_cpu(attr_b->nres.alloc_size)); evcn = le64_to_cpu(attr->nres.evcn); if (end < next_svcn) end = next_svcn; while (end > evcn) { /* Remove segment [svcn : evcn). */ mi_remove_attr(NULL, mi, attr); if (!al_remove_le(ni, le)) { err = -EINVAL; goto out; } if (evcn + 1 >= alloc) { /* Last attribute segment. */ evcn1 = evcn + 1; goto ins_ext; } if (ni_load_mi(ni, le, &mi)) { attr = NULL; goto out; } attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, &le->id); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); } if (end < svcn) end = svcn; err = attr_load_runs(attr, ni, run, &end); if (err) goto out; evcn1 = evcn + 1; attr->nres.svcn = cpu_to_le64(next_svcn); err = mi_pack_runs(mi, attr, run, evcn1 - next_svcn); if (err) goto out; le->vcn = cpu_to_le64(next_svcn); ni->attr_list.dirty = true; mi->dirty = true; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; ins_ext: if (evcn1 > next_svcn) { err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - next_svcn, attr_b->flags, &attr, &mi, NULL); if (err) goto out; } ok: run_truncate_around(run, vcn); out: if (err && step > 1) { /* Too complex to restore. */ _ntfs_bad_inode(&ni->vfs_inode); } up_write(&ni->file.run_lock); ni_unlock(ni); return err; undo1: /* Undo step1. */ attr_b->nres.total_size = cpu_to_le64(total_size0); inode_set_bytes(&ni->vfs_inode, total_size0); if (run_deallocate_ex(sbi, run, vcn, alen, NULL, false) || !run_add_entry(run, vcn, SPARSE_LCN, alen, false) || mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn)) { _ntfs_bad_inode(&ni->vfs_inode); } goto out; } int attr_data_read_resident(struct ntfs_inode *ni, struct folio *folio) { u64 vbo; struct ATTRIB *attr; u32 data_size; size_t len; attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, NULL); if (!attr) return -EINVAL; if (attr->non_res) return E_NTFS_NONRESIDENT; vbo = folio->index << PAGE_SHIFT; data_size = le32_to_cpu(attr->res.data_size); if (vbo > data_size) len = 0; else len = min(data_size - vbo, folio_size(folio)); folio_fill_tail(folio, 0, resident_data(attr) + vbo, len); folio_mark_uptodate(folio); return 0; } int attr_data_write_resident(struct ntfs_inode *ni, struct folio *folio) { u64 vbo; struct mft_inode *mi; struct ATTRIB *attr; u32 data_size; attr = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, &mi); if (!attr) return -EINVAL; if (attr->non_res) { /* Return special error code to check this case. */ return E_NTFS_NONRESIDENT; } vbo = folio->index << PAGE_SHIFT; data_size = le32_to_cpu(attr->res.data_size); if (vbo < data_size) { char *data = resident_data(attr); size_t len = min(data_size - vbo, folio_size(folio)); memcpy_from_folio(data + vbo, folio, 0, len); mi->dirty = true; } ni->i_valid = data_size; return 0; } /* * attr_load_runs_vcn - Load runs with VCN. */ int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct runs_tree *run, CLST vcn) { struct ATTRIB *attr; int err; CLST svcn, evcn; u16 ro; if (!ni) { /* Is record corrupted? */ return -ENOENT; } attr = ni_find_attr(ni, NULL, NULL, type, name, name_len, &vcn, NULL); if (!attr) { /* Is record corrupted? */ return -ENOENT; } svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); if (evcn < vcn || vcn < svcn) { /* Is record corrupted? */ return -EINVAL; } ro = le16_to_cpu(attr->nres.run_off); if (ro > le32_to_cpu(attr->size)) return -EINVAL; err = run_unpack_ex(run, ni->mi.sbi, ni->mi.rno, svcn, evcn, svcn, Add2Ptr(attr, ro), le32_to_cpu(attr->size) - ro); if (err < 0) return err; return 0; } /* * attr_load_runs_range - Load runs for given range [from to). */ int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct runs_tree *run, u64 from, u64 to) { struct ntfs_sb_info *sbi = ni->mi.sbi; u8 cluster_bits = sbi->cluster_bits; CLST vcn; CLST vcn_last = (to - 1) >> cluster_bits; CLST lcn, clen; int err; for (vcn = from >> cluster_bits; vcn <= vcn_last; vcn += clen) { if (!run_lookup_entry(run, vcn, &lcn, &clen, NULL)) { err = attr_load_runs_vcn(ni, type, name, name_len, run, vcn); if (err) return err; clen = 0; /* Next run_lookup_entry(vcn) must be success. */ } } return 0; } #ifdef CONFIG_NTFS3_LZX_XPRESS /* * attr_wof_frame_info * * Read header of Xpress/LZX file to get info about frame. */ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, struct runs_tree *run, u64 frame, u64 frames, u8 frame_bits, u32 *ondisk_size, u64 *vbo_data) { struct ntfs_sb_info *sbi = ni->mi.sbi; u64 vbo[2], off[2], wof_size; u32 voff; u8 bytes_per_off; char *addr; struct folio *folio; int i, err; __le32 *off32; __le64 *off64; if (ni->vfs_inode.i_size < 0x100000000ull) { /* File starts with array of 32 bit offsets. */ bytes_per_off = sizeof(__le32); vbo[1] = frame << 2; *vbo_data = frames << 2; } else { /* File starts with array of 64 bit offsets. */ bytes_per_off = sizeof(__le64); vbo[1] = frame << 3; *vbo_data = frames << 3; } /* * Read 4/8 bytes at [vbo - 4(8)] == offset where compressed frame starts. * Read 4/8 bytes at [vbo] == offset where compressed frame ends. */ if (!attr->non_res) { if (vbo[1] + bytes_per_off > le32_to_cpu(attr->res.data_size)) { ntfs_inode_err(&ni->vfs_inode, "is corrupted"); return -EINVAL; } addr = resident_data(attr); if (bytes_per_off == sizeof(__le32)) { off32 = Add2Ptr(addr, vbo[1]); off[0] = vbo[1] ? le32_to_cpu(off32[-1]) : 0; off[1] = le32_to_cpu(off32[0]); } else { off64 = Add2Ptr(addr, vbo[1]); off[0] = vbo[1] ? le64_to_cpu(off64[-1]) : 0; off[1] = le64_to_cpu(off64[0]); } *vbo_data += off[0]; *ondisk_size = off[1] - off[0]; return 0; } wof_size = le64_to_cpu(attr->nres.data_size); down_write(&ni->file.run_lock); folio = ni->file.offs_folio; if (!folio) { folio = folio_alloc(GFP_KERNEL, 0); if (!folio) { err = -ENOMEM; goto out; } folio->index = -1; ni->file.offs_folio = folio; } folio_lock(folio); addr = folio_address(folio); if (vbo[1]) { voff = vbo[1] & (PAGE_SIZE - 1); vbo[0] = vbo[1] - bytes_per_off; i = 0; } else { voff = 0; vbo[0] = 0; off[0] = 0; i = 1; } do { pgoff_t index = vbo[i] >> PAGE_SHIFT; if (index != folio->index) { struct page *page = &folio->page; u64 from = vbo[i] & ~(u64)(PAGE_SIZE - 1); u64 to = min(from + PAGE_SIZE, wof_size); err = attr_load_runs_range(ni, ATTR_DATA, WOF_NAME, ARRAY_SIZE(WOF_NAME), run, from, to); if (err) goto out1; err = ntfs_bio_pages(sbi, run, &page, 1, from, to - from, REQ_OP_READ); if (err) { folio->index = -1; goto out1; } folio->index = index; } if (i) { if (bytes_per_off == sizeof(__le32)) { off32 = Add2Ptr(addr, voff); off[1] = le32_to_cpu(*off32); } else { off64 = Add2Ptr(addr, voff); off[1] = le64_to_cpu(*off64); } } else if (!voff) { if (bytes_per_off == sizeof(__le32)) { off32 = Add2Ptr(addr, PAGE_SIZE - sizeof(u32)); off[0] = le32_to_cpu(*off32); } else { off64 = Add2Ptr(addr, PAGE_SIZE - sizeof(u64)); off[0] = le64_to_cpu(*off64); } } else { /* Two values in one page. */ if (bytes_per_off == sizeof(__le32)) { off32 = Add2Ptr(addr, voff); off[0] = le32_to_cpu(off32[-1]); off[1] = le32_to_cpu(off32[0]); } else { off64 = Add2Ptr(addr, voff); off[0] = le64_to_cpu(off64[-1]); off[1] = le64_to_cpu(off64[0]); } break; } } while (++i < 2); *vbo_data += off[0]; *ondisk_size = off[1] - off[0]; out1: folio_unlock(folio); out: up_write(&ni->file.run_lock); return err; } #endif /* * attr_is_frame_compressed - Used to detect compressed frame. */ int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr, CLST frame, CLST *clst_data) { int err; u32 clst_frame; CLST clen, lcn, vcn, alen, slen, vcn_next; size_t idx; struct runs_tree *run; *clst_data = 0; if (!is_attr_compressed(attr)) return 0; if (!attr->non_res) return 0; clst_frame = 1u << attr->nres.c_unit; vcn = frame * clst_frame; run = &ni->file.run; if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) { err = attr_load_runs_vcn(ni, attr->type, attr_name(attr), attr->name_len, run, vcn); if (err) return err; if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) return -EINVAL; } if (lcn == SPARSE_LCN) { /* Sparsed frame. */ return 0; } if (clen >= clst_frame) { /* * The frame is not compressed 'cause * it does not contain any sparse clusters. */ *clst_data = clst_frame; return 0; } alen = bytes_to_cluster(ni->mi.sbi, le64_to_cpu(attr->nres.alloc_size)); slen = 0; *clst_data = clen; /* * The frame is compressed if *clst_data + slen >= clst_frame. * Check next fragments. */ while ((vcn += clen) < alen) { vcn_next = vcn; if (!run_get_entry(run, ++idx, &vcn, &lcn, &clen) || vcn_next != vcn) { err = attr_load_runs_vcn(ni, attr->type, attr_name(attr), attr->name_len, run, vcn_next); if (err) return err; vcn = vcn_next; if (!run_lookup_entry(run, vcn, &lcn, &clen, &idx)) return -EINVAL; } if (lcn == SPARSE_LCN) { slen += clen; } else { if (slen) { /* * Data_clusters + sparse_clusters = * not enough for frame. */ return -EINVAL; } *clst_data += clen; } if (*clst_data + slen >= clst_frame) { if (!slen) { /* * There is no sparsed clusters in this frame * so it is not compressed. */ *clst_data = clst_frame; } else { /* Frame is compressed. */ } break; } } return 0; } /* * attr_allocate_frame - Allocate/free clusters for @frame. * * Assumed: down_write(&ni->file.run_lock); */ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, u64 new_valid) { int err = 0; struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi = ni->mi.sbi; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST svcn, evcn1, next_svcn, len; CLST vcn, end, clst_data; u64 total_size, valid_size, data_size; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) return -ENOENT; if (!is_attr_ext(attr_b)) return -EINVAL; vcn = frame << NTFS_LZNT_CUNIT; total_size = le64_to_cpu(attr_b->nres.total_size); svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; data_size = le64_to_cpu(attr_b->nres.data_size); if (svcn <= vcn && vcn < evcn1) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto out; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; err = attr_is_frame_compressed(ni, attr_b, frame, &clst_data); if (err) goto out; total_size -= (u64)clst_data << sbi->cluster_bits; len = bytes_to_cluster(sbi, compr_size); if (len == clst_data) goto out; if (len < clst_data) { err = run_deallocate_ex(sbi, run, vcn + len, clst_data - len, NULL, true); if (err) goto out; if (!run_add_entry(run, vcn + len, SPARSE_LCN, clst_data - len, false)) { err = -ENOMEM; goto out; } end = vcn + clst_data; /* Run contains updated range [vcn + len : end). */ } else { CLST alen, hint = 0; /* Get the last LCN to allocate from. */ if (vcn + clst_data && !run_lookup_entry(run, vcn + clst_data - 1, &hint, NULL, NULL)) { hint = -1; } err = attr_allocate_clusters(sbi, run, vcn + clst_data, hint + 1, len - clst_data, NULL, ALLOCATE_DEF, &alen, 0, NULL, NULL); if (err) goto out; end = vcn + len; /* Run contains updated range [vcn + clst_data : end). */ } total_size += (u64)len << sbi->cluster_bits; repack: err = mi_pack_runs(mi, attr, run, max(end, evcn1) - svcn); if (err) goto out; attr_b->nres.total_size = cpu_to_le64(total_size); inode_set_bytes(&ni->vfs_inode, total_size); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mi_b->dirty = true; mark_inode_dirty(&ni->vfs_inode); /* Stored [vcn : next_svcn) from [vcn : end). */ next_svcn = le64_to_cpu(attr->nres.evcn) + 1; if (end <= evcn1) { if (next_svcn == evcn1) { /* Normal way. Update attribute and exit. */ goto ok; } /* Add new segment [next_svcn : evcn1 - next_svcn). */ if (!ni->attr_list.size) { err = ni_create_attr_list(ni); if (err) goto out; /* Layout of records is changed. */ le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -ENOENT; goto out; } attr = attr_b; le = le_b; mi = mi_b; goto repack; } } svcn = evcn1; /* Estimate next attribute. */ attr = ni_find_attr(ni, attr, &le, ATTR_DATA, NULL, 0, &svcn, &mi); if (attr) { CLST alloc = bytes_to_cluster( sbi, le64_to_cpu(attr_b->nres.alloc_size)); CLST evcn = le64_to_cpu(attr->nres.evcn); if (end < next_svcn) end = next_svcn; while (end > evcn) { /* Remove segment [svcn : evcn). */ mi_remove_attr(NULL, mi, attr); if (!al_remove_le(ni, le)) { err = -EINVAL; goto out; } if (evcn + 1 >= alloc) { /* Last attribute segment. */ evcn1 = evcn + 1; goto ins_ext; } if (ni_load_mi(ni, le, &mi)) { attr = NULL; goto out; } attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, &le->id); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); } if (end < svcn) end = svcn; err = attr_load_runs(attr, ni, run, &end); if (err) goto out; evcn1 = evcn + 1; attr->nres.svcn = cpu_to_le64(next_svcn); err = mi_pack_runs(mi, attr, run, evcn1 - next_svcn); if (err) goto out; le->vcn = cpu_to_le64(next_svcn); ni->attr_list.dirty = true; mi->dirty = true; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; } ins_ext: if (evcn1 > next_svcn) { err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - next_svcn, attr_b->flags, &attr, &mi, NULL); if (err) goto out; } ok: run_truncate_around(run, vcn); out: if (attr_b) { if (new_valid > data_size) new_valid = data_size; valid_size = le64_to_cpu(attr_b->nres.valid_size); if (new_valid != valid_size) { attr_b->nres.valid_size = cpu_to_le64(valid_size); mi_b->dirty = true; } } return err; } /* * attr_collapse_range - Collapse range in file. */ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) { int err = 0; struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi = ni->mi.sbi; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST svcn, evcn1, len, dealloc, alen; CLST vcn, end; u64 valid_size, data_size, alloc_size, total_size; u32 mask; __le16 a_flags; if (!bytes) return 0; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) return -ENOENT; if (!attr_b->non_res) { /* Attribute is resident. Nothing to do? */ return 0; } data_size = le64_to_cpu(attr_b->nres.data_size); alloc_size = le64_to_cpu(attr_b->nres.alloc_size); a_flags = attr_b->flags; if (is_attr_ext(attr_b)) { total_size = le64_to_cpu(attr_b->nres.total_size); mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; } else { total_size = alloc_size; mask = sbi->cluster_mask; } if ((vbo & mask) || (bytes & mask)) { /* Allow to collapse only cluster aligned ranges. */ return -EINVAL; } if (vbo > data_size) return -EINVAL; down_write(&ni->file.run_lock); if (vbo + bytes >= data_size) { u64 new_valid = min(ni->i_valid, vbo); /* Simple truncate file at 'vbo'. */ truncate_setsize(&ni->vfs_inode, vbo); err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, vbo, &new_valid, true, NULL); if (!err && new_valid < ni->i_valid) ni->i_valid = new_valid; goto out; } /* * Enumerate all attribute segments and collapse. */ alen = alloc_size >> sbi->cluster_bits; vcn = vbo >> sbi->cluster_bits; len = bytes >> sbi->cluster_bits; end = vcn + len; dealloc = 0; svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; if (svcn <= vcn && vcn < evcn1) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto out; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto out; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } for (;;) { if (svcn >= end) { /* Shift VCN- */ attr->nres.svcn = cpu_to_le64(svcn - len); attr->nres.evcn = cpu_to_le64(evcn1 - 1 - len); if (le) { le->vcn = attr->nres.svcn; ni->attr_list.dirty = true; } mi->dirty = true; } else if (svcn < vcn || end < evcn1) { CLST vcn1, eat, next_svcn; /* Collapse a part of this attribute segment. */ err = attr_load_runs(attr, ni, run, &svcn); if (err) goto out; vcn1 = max(vcn, svcn); eat = min(end, evcn1) - vcn1; err = run_deallocate_ex(sbi, run, vcn1, eat, &dealloc, true); if (err) goto out; if (!run_collapse_range(run, vcn1, eat)) { err = -ENOMEM; goto out; } if (svcn >= vcn) { /* Shift VCN */ attr->nres.svcn = cpu_to_le64(vcn); if (le) { le->vcn = attr->nres.svcn; ni->attr_list.dirty = true; } } err = mi_pack_runs(mi, attr, run, evcn1 - svcn - eat); if (err) goto out; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; if (next_svcn + eat < evcn1) { err = ni_insert_nonresident( ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - eat - next_svcn, a_flags, &attr, &mi, &le); if (err) goto out; /* Layout of records maybe changed. */ attr_b = NULL; } /* Free all allocated memory. */ run_truncate(run, 0); } else { u16 le_sz; u16 roff = le16_to_cpu(attr->nres.run_off); if (roff > le32_to_cpu(attr->size)) { err = -EINVAL; goto out; } run_unpack_ex(RUN_DEALLOCATE, sbi, ni->mi.rno, svcn, evcn1 - 1, svcn, Add2Ptr(attr, roff), le32_to_cpu(attr->size) - roff); /* Delete this attribute segment. */ mi_remove_attr(NULL, mi, attr); if (!le) break; le_sz = le16_to_cpu(le->size); if (!al_remove_le(ni, le)) { err = -EINVAL; goto out; } if (evcn1 >= alen) break; if (!svcn) { /* Load next record that contains this attribute. */ if (ni_load_mi(ni, le, &mi)) { err = -EINVAL; goto out; } /* Look for required attribute. */ attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, &le->id); if (!attr) { err = -EINVAL; goto out; } goto next_attr; } le = (struct ATTR_LIST_ENTRY *)((u8 *)le - le_sz); } if (evcn1 >= alen) break; attr = ni_enum_attr_ex(ni, attr, &le, &mi); if (!attr) { err = -EINVAL; goto out; } next_attr: svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } if (!attr_b) { le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -ENOENT; goto out; } } data_size -= bytes; valid_size = ni->i_valid; if (vbo + bytes <= valid_size) valid_size -= bytes; else if (vbo < valid_size) valid_size = vbo; attr_b->nres.alloc_size = cpu_to_le64(alloc_size - bytes); attr_b->nres.data_size = cpu_to_le64(data_size); attr_b->nres.valid_size = cpu_to_le64(min(valid_size, data_size)); total_size -= (u64)dealloc << sbi->cluster_bits; if (is_attr_ext(attr_b)) attr_b->nres.total_size = cpu_to_le64(total_size); mi_b->dirty = true; /* Update inode size. */ ni->i_valid = valid_size; i_size_write(&ni->vfs_inode, data_size); inode_set_bytes(&ni->vfs_inode, total_size); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mark_inode_dirty(&ni->vfs_inode); out: up_write(&ni->file.run_lock); if (err) _ntfs_bad_inode(&ni->vfs_inode); return err; } /* * attr_punch_hole * * Not for normal files. */ int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size) { int err = 0; struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi = ni->mi.sbi; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST svcn, evcn1, vcn, len, end, alen, hole, next_svcn; u64 total_size, alloc_size; u32 mask; __le16 a_flags; struct runs_tree run2; if (!bytes) return 0; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) return -ENOENT; if (!attr_b->non_res) { u32 data_size = le32_to_cpu(attr_b->res.data_size); u32 from, to; if (vbo > data_size) return 0; from = vbo; to = min_t(u64, vbo + bytes, data_size); memset(Add2Ptr(resident_data(attr_b), from), 0, to - from); return 0; } if (!is_attr_ext(attr_b)) return -EOPNOTSUPP; alloc_size = le64_to_cpu(attr_b->nres.alloc_size); total_size = le64_to_cpu(attr_b->nres.total_size); if (vbo >= alloc_size) { /* NOTE: It is allowed. */ return 0; } mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; bytes += vbo; if (bytes > alloc_size) bytes = alloc_size; bytes -= vbo; if ((vbo & mask) || (bytes & mask)) { /* We have to zero a range(s). */ if (frame_size == NULL) { /* Caller insists range is aligned. */ return -EINVAL; } *frame_size = mask + 1; return E_NTFS_NOTALIGNED; } down_write(&ni->file.run_lock); run_init(&run2); run_truncate(run, 0); /* * Enumerate all attribute segments and punch hole where necessary. */ alen = alloc_size >> sbi->cluster_bits; vcn = vbo >> sbi->cluster_bits; len = bytes >> sbi->cluster_bits; end = vcn + len; hole = 0; svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; a_flags = attr_b->flags; if (svcn <= vcn && vcn < evcn1) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } while (svcn < end) { CLST vcn1, zero, hole2 = hole; err = attr_load_runs(attr, ni, run, &svcn); if (err) goto done; vcn1 = max(vcn, svcn); zero = min(end, evcn1) - vcn1; /* * Check range [vcn1 + zero). * Calculate how many clusters there are. * Don't do any destructive actions. */ err = run_deallocate_ex(NULL, run, vcn1, zero, &hole2, false); if (err) goto done; /* Check if required range is already hole. */ if (hole2 == hole) goto next_attr; /* Make a clone of run to undo. */ err = run_clone(run, &run2); if (err) goto done; /* Make a hole range (sparse) [vcn1 + zero). */ if (!run_add_entry(run, vcn1, SPARSE_LCN, zero, false)) { err = -ENOMEM; goto done; } /* Update run in attribute segment. */ err = mi_pack_runs(mi, attr, run, evcn1 - svcn); if (err) goto done; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; if (next_svcn < evcn1) { /* Insert new attribute segment. */ err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 - next_svcn, a_flags, &attr, &mi, &le); if (err) goto undo_punch; /* Layout of records maybe changed. */ attr_b = NULL; } /* Real deallocate. Should not fail. */ run_deallocate_ex(sbi, &run2, vcn1, zero, &hole, true); next_attr: /* Free all allocated memory. */ run_truncate(run, 0); if (evcn1 >= alen) break; /* Get next attribute segment. */ attr = ni_enum_attr_ex(ni, attr, &le, &mi); if (!attr) { err = -EINVAL; goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } done: if (!hole) goto out; if (!attr_b) { attr_b = ni_find_attr(ni, NULL, NULL, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -EINVAL; goto bad_inode; } } total_size -= (u64)hole << sbi->cluster_bits; attr_b->nres.total_size = cpu_to_le64(total_size); mi_b->dirty = true; /* Update inode size. */ inode_set_bytes(&ni->vfs_inode, total_size); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mark_inode_dirty(&ni->vfs_inode); out: run_close(&run2); up_write(&ni->file.run_lock); return err; bad_inode: _ntfs_bad_inode(&ni->vfs_inode); goto out; undo_punch: /* * Restore packed runs. * 'mi_pack_runs' should not fail, cause we restore original. */ if (mi_pack_runs(mi, attr, &run2, evcn1 - svcn)) goto bad_inode; goto done; } /* * attr_insert_range - Insert range (hole) in file. * Not for normal files. */ int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) { int err = 0; struct runs_tree *run = &ni->file.run; struct ntfs_sb_info *sbi = ni->mi.sbi; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; struct mft_inode *mi, *mi_b; CLST vcn, svcn, evcn1, len, next_svcn; u64 data_size, alloc_size; u32 mask; __le16 a_flags; if (!bytes) return 0; le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) return -ENOENT; if (!is_attr_ext(attr_b)) { /* It was checked above. See fallocate. */ return -EOPNOTSUPP; } if (!attr_b->non_res) { data_size = le32_to_cpu(attr_b->res.data_size); alloc_size = data_size; mask = sbi->cluster_mask; /* cluster_size - 1 */ } else { data_size = le64_to_cpu(attr_b->nres.data_size); alloc_size = le64_to_cpu(attr_b->nres.alloc_size); mask = (sbi->cluster_size << attr_b->nres.c_unit) - 1; } if (vbo >= data_size) { /* * Insert range after the file size is not allowed. * If the offset is equal to or greater than the end of * file, an error is returned. For such operations (i.e., inserting * a hole at the end of file), ftruncate(2) should be used. */ return -EINVAL; } if ((vbo & mask) || (bytes & mask)) { /* Allow to insert only frame aligned ranges. */ return -EINVAL; } /* * valid_size <= data_size <= alloc_size * Check alloc_size for maximum possible. */ if (bytes > sbi->maxbytes_sparse - alloc_size) return -EFBIG; vcn = vbo >> sbi->cluster_bits; len = bytes >> sbi->cluster_bits; down_write(&ni->file.run_lock); if (!attr_b->non_res) { err = attr_set_size(ni, ATTR_DATA, NULL, 0, run, data_size + bytes, NULL, false, NULL); le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -EINVAL; goto bad_inode; } if (err) goto out; if (!attr_b->non_res) { /* Still resident. */ char *data = Add2Ptr(attr_b, le16_to_cpu(attr_b->res.data_off)); memmove(data + bytes, data, bytes); memset(data, 0, bytes); goto done; } /* Resident files becomes nonresident. */ data_size = le64_to_cpu(attr_b->nres.data_size); alloc_size = le64_to_cpu(attr_b->nres.alloc_size); } /* * Enumerate all attribute segments and shift start vcn. */ a_flags = attr_b->flags; svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; if (svcn <= vcn && vcn < evcn1) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { err = -EINVAL; goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { err = -EINVAL; goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } run_truncate(run, 0); /* clear cached values. */ err = attr_load_runs(attr, ni, run, NULL); if (err) goto out; if (!run_insert_range(run, vcn, len)) { err = -ENOMEM; goto out; } /* Try to pack in current record as much as possible. */ err = mi_pack_runs(mi, attr, run, evcn1 + len - svcn); if (err) goto out; next_svcn = le64_to_cpu(attr->nres.evcn) + 1; while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi)) && attr->type == ATTR_DATA && !attr->name_len) { le64_add_cpu(&attr->nres.svcn, len); le64_add_cpu(&attr->nres.evcn, len); if (le) { le->vcn = attr->nres.svcn; ni->attr_list.dirty = true; } mi->dirty = true; } if (next_svcn < evcn1 + len) { err = ni_insert_nonresident(ni, ATTR_DATA, NULL, 0, run, next_svcn, evcn1 + len - next_svcn, a_flags, NULL, NULL, NULL); le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); if (!attr_b) { err = -EINVAL; goto bad_inode; } if (err) { /* ni_insert_nonresident failed. Try to undo. */ goto undo_insert_range; } } /* * Update primary attribute segment. */ if (vbo <= ni->i_valid) ni->i_valid += bytes; attr_b->nres.data_size = cpu_to_le64(data_size + bytes); attr_b->nres.alloc_size = cpu_to_le64(alloc_size + bytes); /* ni->valid may be not equal valid_size (temporary). */ if (ni->i_valid > data_size + bytes) attr_b->nres.valid_size = attr_b->nres.data_size; else attr_b->nres.valid_size = cpu_to_le64(ni->i_valid); mi_b->dirty = true; done: i_size_write(&ni->vfs_inode, ni->vfs_inode.i_size + bytes); ni->ni_flags |= NI_FLAG_UPDATE_PARENT; mark_inode_dirty(&ni->vfs_inode); out: run_truncate(run, 0); /* clear cached values. */ up_write(&ni->file.run_lock); return err; bad_inode: _ntfs_bad_inode(&ni->vfs_inode); goto out; undo_insert_range: svcn = le64_to_cpu(attr_b->nres.svcn); evcn1 = le64_to_cpu(attr_b->nres.evcn) + 1; if (svcn <= vcn && vcn < evcn1) { attr = attr_b; le = le_b; mi = mi_b; } else if (!le_b) { goto bad_inode; } else { le = le_b; attr = ni_find_attr(ni, attr_b, &le, ATTR_DATA, NULL, 0, &vcn, &mi); if (!attr) { goto bad_inode; } svcn = le64_to_cpu(attr->nres.svcn); evcn1 = le64_to_cpu(attr->nres.evcn) + 1; } if (attr_load_runs(attr, ni, run, NULL)) goto bad_inode; if (!run_collapse_range(run, vcn, len)) goto bad_inode; if (mi_pack_runs(mi, attr, run, evcn1 + len - svcn)) goto bad_inode; while ((attr = ni_enum_attr_ex(ni, attr, &le, &mi)) && attr->type == ATTR_DATA && !attr->name_len) { le64_sub_cpu(&attr->nres.svcn, len); le64_sub_cpu(&attr->nres.evcn, len); if (le) { le->vcn = attr->nres.svcn; ni->attr_list.dirty = true; } mi->dirty = true; } goto out; } /* * attr_force_nonresident * * Convert default data attribute into non resident form. */ int attr_force_nonresident(struct ntfs_inode *ni) { int err; struct ATTRIB *attr; struct ATTR_LIST_ENTRY *le = NULL; struct mft_inode *mi; attr = ni_find_attr(ni, NULL, &le, ATTR_DATA, NULL, 0, NULL, &mi); if (!attr) { ntfs_bad_inode(&ni->vfs_inode, "no data attribute"); return -ENOENT; } if (attr->non_res) { /* Already non resident. */ return 0; } down_write(&ni->file.run_lock); err = attr_make_nonresident(ni, attr, le, mi, le32_to_cpu(attr->res.data_size), &ni->file.run, &attr, NULL); up_write(&ni->file.run_lock); return err; } |
| 87 5 92 92 1 87 86 86 86 1 2 83 83 83 83 55 55 55 92 92 156 157 154 18 92 92 1 92 140 140 182 149 182 71 149 26 26 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 | // SPDX-License-Identifier: GPL-2.0-only /* * vfsv0 quota IO operations on file */ #include <linux/errno.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/dqblk_v2.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/quotaops.h> #include <asm/byteorder.h> #include "quota_tree.h" #include "quotaio_v2.h" MODULE_AUTHOR("Jan Kara"); MODULE_DESCRIPTION("Quota format v2 support"); MODULE_LICENSE("GPL"); static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot); static void v2r0_disk2memdqb(struct dquot *dquot, void *dp); static int v2r0_is_id(void *dp, struct dquot *dquot); static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot); static void v2r1_disk2memdqb(struct dquot *dquot, void *dp); static int v2r1_is_id(void *dp, struct dquot *dquot); static const struct qtree_fmt_operations v2r0_qtree_ops = { .mem2disk_dqblk = v2r0_mem2diskdqb, .disk2mem_dqblk = v2r0_disk2memdqb, .is_id = v2r0_is_id, }; static const struct qtree_fmt_operations v2r1_qtree_ops = { .mem2disk_dqblk = v2r1_mem2diskdqb, .disk2mem_dqblk = v2r1_disk2memdqb, .is_id = v2r1_is_id, }; #define QUOTABLOCK_BITS 10 #define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS) static inline qsize_t v2_stoqb(qsize_t space) { return (space + QUOTABLOCK_SIZE - 1) >> QUOTABLOCK_BITS; } static inline qsize_t v2_qbtos(qsize_t blocks) { return blocks << QUOTABLOCK_BITS; } static int v2_read_header(struct super_block *sb, int type, struct v2_disk_dqheader *dqhead) { ssize_t size; size = sb->s_op->quota_read(sb, type, (char *)dqhead, sizeof(struct v2_disk_dqheader), 0); if (size != sizeof(struct v2_disk_dqheader)) { quota_error(sb, "Failed header read: expected=%zd got=%zd", sizeof(struct v2_disk_dqheader), size); if (size < 0) return size; return -EIO; } return 0; } /* Check whether given file is really vfsv0 quotafile */ static int v2_check_quota_file(struct super_block *sb, int type) { struct v2_disk_dqheader dqhead; static const uint quota_magics[] = V2_INITQMAGICS; static const uint quota_versions[] = V2_INITQVERSIONS; if (v2_read_header(sb, type, &dqhead)) return 0; if (le32_to_cpu(dqhead.dqh_magic) != quota_magics[type] || le32_to_cpu(dqhead.dqh_version) > quota_versions[type]) return 0; return 1; } /* Read information header from quota file */ static int v2_read_file_info(struct super_block *sb, int type) { struct v2_disk_dqinfo dinfo; struct v2_disk_dqheader dqhead; struct quota_info *dqopt = sb_dqopt(sb); struct mem_dqinfo *info = &dqopt->info[type]; struct qtree_mem_dqinfo *qinfo; ssize_t size; unsigned int version; unsigned int memalloc; int ret; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = v2_read_header(sb, type, &dqhead); if (ret < 0) goto out; version = le32_to_cpu(dqhead.dqh_version); if ((info->dqi_fmt_id == QFMT_VFS_V0 && version != 0) || (info->dqi_fmt_id == QFMT_VFS_V1 && version != 1)) { ret = -EINVAL; goto out; } size = sb->s_op->quota_read(sb, type, (char *)&dinfo, sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF); if (size != sizeof(struct v2_disk_dqinfo)) { quota_error(sb, "Can't read info structure"); if (size < 0) ret = size; else ret = -EIO; goto out; } info->dqi_priv = kmalloc(sizeof(struct qtree_mem_dqinfo), GFP_KERNEL); if (!info->dqi_priv) { ret = -ENOMEM; goto out; } qinfo = info->dqi_priv; if (version == 0) { /* limits are stored as unsigned 32-bit data */ info->dqi_max_spc_limit = 0xffffffffLL << QUOTABLOCK_BITS; info->dqi_max_ino_limit = 0xffffffff; } else { /* * Used space is stored as unsigned 64-bit value in bytes but * quota core supports only signed 64-bit values so use that * as a limit */ info->dqi_max_spc_limit = 0x7fffffffffffffffLL; /* 2^63-1 */ info->dqi_max_ino_limit = 0x7fffffffffffffffLL; } info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); /* No flags currently supported */ info->dqi_flags = 0; qinfo->dqi_sb = sb; qinfo->dqi_type = type; qinfo->dqi_blocks = le32_to_cpu(dinfo.dqi_blocks); qinfo->dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk); qinfo->dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry); qinfo->dqi_blocksize_bits = V2_DQBLKSIZE_BITS; qinfo->dqi_usable_bs = 1 << V2_DQBLKSIZE_BITS; qinfo->dqi_qtree_depth = qtree_depth(qinfo); if (version == 0) { qinfo->dqi_entry_size = sizeof(struct v2r0_disk_dqblk); qinfo->dqi_ops = &v2r0_qtree_ops; } else { qinfo->dqi_entry_size = sizeof(struct v2r1_disk_dqblk); qinfo->dqi_ops = &v2r1_qtree_ops; } ret = -EUCLEAN; /* Some sanity checks of the read headers... */ if ((loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits > i_size_read(sb_dqopt(sb)->files[type])) { quota_error(sb, "Number of blocks too big for quota file size (%llu > %llu).", (loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits, i_size_read(sb_dqopt(sb)->files[type])); goto out_free; } if (qinfo->dqi_free_blk && (qinfo->dqi_free_blk <= QT_TREEOFF || qinfo->dqi_free_blk >= qinfo->dqi_blocks)) { quota_error(sb, "Free block number %u out of range (%u, %u).", qinfo->dqi_free_blk, QT_TREEOFF, qinfo->dqi_blocks); goto out_free; } if (qinfo->dqi_free_entry && (qinfo->dqi_free_entry <= QT_TREEOFF || qinfo->dqi_free_entry >= qinfo->dqi_blocks)) { quota_error(sb, "Block with free entry %u out of range (%u, %u).", qinfo->dqi_free_entry, QT_TREEOFF, qinfo->dqi_blocks); goto out_free; } ret = 0; out_free: if (ret) { kfree(info->dqi_priv); info->dqi_priv = NULL; } out: memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } /* Write information header to quota file */ static int v2_write_file_info(struct super_block *sb, int type) { struct v2_disk_dqinfo dinfo; struct quota_info *dqopt = sb_dqopt(sb); struct mem_dqinfo *info = &dqopt->info[type]; struct qtree_mem_dqinfo *qinfo = info->dqi_priv; ssize_t size; unsigned int memalloc; down_write(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); spin_lock(&dq_data_lock); info->dqi_flags &= ~DQF_INFO_DIRTY; dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace); dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace); /* No flags currently supported */ dinfo.dqi_flags = cpu_to_le32(0); spin_unlock(&dq_data_lock); dinfo.dqi_blocks = cpu_to_le32(qinfo->dqi_blocks); dinfo.dqi_free_blk = cpu_to_le32(qinfo->dqi_free_blk); dinfo.dqi_free_entry = cpu_to_le32(qinfo->dqi_free_entry); size = sb->s_op->quota_write(sb, type, (char *)&dinfo, sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF); memalloc_nofs_restore(memalloc); up_write(&dqopt->dqio_sem); if (size != sizeof(struct v2_disk_dqinfo)) { quota_error(sb, "Can't write info structure"); return size < 0 ? size : -EIO; } return 0; } static void v2r0_disk2memdqb(struct dquot *dquot, void *dp) { struct v2r0_disk_dqblk *d = dp, empty; struct mem_dqblk *m = &dquot->dq_dqb; m->dqb_ihardlimit = le32_to_cpu(d->dqb_ihardlimit); m->dqb_isoftlimit = le32_to_cpu(d->dqb_isoftlimit); m->dqb_curinodes = le32_to_cpu(d->dqb_curinodes); m->dqb_itime = le64_to_cpu(d->dqb_itime); m->dqb_bhardlimit = v2_qbtos(le32_to_cpu(d->dqb_bhardlimit)); m->dqb_bsoftlimit = v2_qbtos(le32_to_cpu(d->dqb_bsoftlimit)); m->dqb_curspace = le64_to_cpu(d->dqb_curspace); m->dqb_btime = le64_to_cpu(d->dqb_btime); /* We need to escape back all-zero structure */ memset(&empty, 0, sizeof(struct v2r0_disk_dqblk)); empty.dqb_itime = cpu_to_le64(1); if (!memcmp(&empty, dp, sizeof(struct v2r0_disk_dqblk))) m->dqb_itime = 0; } static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot) { struct v2r0_disk_dqblk *d = dp; struct mem_dqblk *m = &dquot->dq_dqb; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; d->dqb_ihardlimit = cpu_to_le32(m->dqb_ihardlimit); d->dqb_isoftlimit = cpu_to_le32(m->dqb_isoftlimit); d->dqb_curinodes = cpu_to_le32(m->dqb_curinodes); d->dqb_itime = cpu_to_le64(m->dqb_itime); d->dqb_bhardlimit = cpu_to_le32(v2_stoqb(m->dqb_bhardlimit)); d->dqb_bsoftlimit = cpu_to_le32(v2_stoqb(m->dqb_bsoftlimit)); d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } static int v2r0_is_id(void *dp, struct dquot *dquot) { struct v2r0_disk_dqblk *d = dp; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; if (qtree_entry_unused(info, dp)) return 0; return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type, le32_to_cpu(d->dqb_id)), dquot->dq_id); } static void v2r1_disk2memdqb(struct dquot *dquot, void *dp) { struct v2r1_disk_dqblk *d = dp, empty; struct mem_dqblk *m = &dquot->dq_dqb; m->dqb_ihardlimit = le64_to_cpu(d->dqb_ihardlimit); m->dqb_isoftlimit = le64_to_cpu(d->dqb_isoftlimit); m->dqb_curinodes = le64_to_cpu(d->dqb_curinodes); m->dqb_itime = le64_to_cpu(d->dqb_itime); m->dqb_bhardlimit = v2_qbtos(le64_to_cpu(d->dqb_bhardlimit)); m->dqb_bsoftlimit = v2_qbtos(le64_to_cpu(d->dqb_bsoftlimit)); m->dqb_curspace = le64_to_cpu(d->dqb_curspace); m->dqb_btime = le64_to_cpu(d->dqb_btime); /* We need to escape back all-zero structure */ memset(&empty, 0, sizeof(struct v2r1_disk_dqblk)); empty.dqb_itime = cpu_to_le64(1); if (!memcmp(&empty, dp, sizeof(struct v2r1_disk_dqblk))) m->dqb_itime = 0; } static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot) { struct v2r1_disk_dqblk *d = dp; struct mem_dqblk *m = &dquot->dq_dqb; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; d->dqb_ihardlimit = cpu_to_le64(m->dqb_ihardlimit); d->dqb_isoftlimit = cpu_to_le64(m->dqb_isoftlimit); d->dqb_curinodes = cpu_to_le64(m->dqb_curinodes); d->dqb_itime = cpu_to_le64(m->dqb_itime); d->dqb_bhardlimit = cpu_to_le64(v2_stoqb(m->dqb_bhardlimit)); d->dqb_bsoftlimit = cpu_to_le64(v2_stoqb(m->dqb_bsoftlimit)); d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); d->dqb_pad = 0; if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } static int v2r1_is_id(void *dp, struct dquot *dquot) { struct v2r1_disk_dqblk *d = dp; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; if (qtree_entry_unused(info, dp)) return 0; return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type, le32_to_cpu(d->dqb_id)), dquot->dq_id); } static int v2_read_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); int ret; unsigned int memalloc; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_read_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } static int v2_write_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); int ret; bool alloc = false; unsigned int memalloc; /* * If space for dquot is already allocated, we don't need any * protection as we'll only overwrite the place of dquot. We are * still protected by concurrent writes of the same dquot by * dquot->dq_lock. */ if (!dquot->dq_off) { alloc = true; down_write(&dqopt->dqio_sem); } else { down_read(&dqopt->dqio_sem); } memalloc = memalloc_nofs_save(); ret = qtree_write_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); if (alloc) up_write(&dqopt->dqio_sem); else up_read(&dqopt->dqio_sem); return ret; } static int v2_release_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); unsigned int memalloc; int ret; down_write(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_release_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); up_write(&dqopt->dqio_sem); return ret; } static int v2_free_file_info(struct super_block *sb, int type) { kfree(sb_dqinfo(sb, type)->dqi_priv); return 0; } static int v2_get_next_id(struct super_block *sb, struct kqid *qid) { struct quota_info *dqopt = sb_dqopt(sb); unsigned int memalloc; int ret; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid); memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } static const struct quota_format_ops v2_format_ops = { .check_quota_file = v2_check_quota_file, .read_file_info = v2_read_file_info, .write_file_info = v2_write_file_info, .free_file_info = v2_free_file_info, .read_dqblk = v2_read_dquot, .commit_dqblk = v2_write_dquot, .release_dqblk = v2_release_dquot, .get_next_id = v2_get_next_id, }; static struct quota_format_type v2r0_quota_format = { .qf_fmt_id = QFMT_VFS_V0, .qf_ops = &v2_format_ops, .qf_owner = THIS_MODULE }; static struct quota_format_type v2r1_quota_format = { .qf_fmt_id = QFMT_VFS_V1, .qf_ops = &v2_format_ops, .qf_owner = THIS_MODULE }; static int __init init_v2_quota_format(void) { int ret; ret = register_quota_format(&v2r0_quota_format); if (ret) return ret; return register_quota_format(&v2r1_quota_format); } static void __exit exit_v2_quota_format(void) { unregister_quota_format(&v2r0_quota_format); unregister_quota_format(&v2r1_quota_format); } module_init(init_v2_quota_format); module_exit(exit_v2_quota_format); |
| 3 10 10 10 10 3 3 10 10 3 6 1 3 4 7 7 5 3 5 10 2 1 7 3 10 10 3 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 | // SPDX-License-Identifier: GPL-2.0-or-later /* AFS dynamic root handling * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/fs.h> #include <linux/namei.h> #include <linux/dns_resolver.h> #include "internal.h" static atomic_t afs_autocell_ino; /* * iget5() comparator for inode created by autocell operations * * These pseudo inodes don't match anything. */ static int afs_iget5_pseudo_test(struct inode *inode, void *opaque) { return 0; } /* * iget5() inode initialiser */ static int afs_iget5_pseudo_set(struct inode *inode, void *opaque) { struct afs_super_info *as = AFS_FS_S(inode->i_sb); struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_fid *fid = opaque; vnode->volume = as->volume; vnode->fid = *fid; inode->i_ino = fid->vnode; inode->i_generation = fid->unique; return 0; } /* * Create an inode for a dynamic root directory or an autocell dynamic * automount dir. */ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) { struct afs_super_info *as = AFS_FS_S(sb); struct afs_vnode *vnode; struct inode *inode; struct afs_fid fid = {}; _enter(""); if (as->volume) fid.vid = as->volume->vid; if (root) { fid.vnode = 1; fid.unique = 1; } else { fid.vnode = atomic_inc_return(&afs_autocell_ino); fid.unique = 0; } inode = iget5_locked(sb, fid.vnode, afs_iget5_pseudo_test, afs_iget5_pseudo_set, &fid); if (!inode) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); } _debug("GOT INODE %p { ino=%lu, vl=%llx, vn=%llx, u=%x }", inode, inode->i_ino, fid.vid, fid.vnode, fid.unique); vnode = AFS_FS_I(inode); /* there shouldn't be an existing inode */ BUG_ON(!(inode->i_state & I_NEW)); netfs_inode_init(&vnode->netfs, NULL, false); inode->i_size = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; if (root) { inode->i_op = &afs_dynroot_inode_operations; inode->i_fop = &simple_dir_operations; } else { inode->i_op = &afs_autocell_inode_operations; } set_nlink(inode, 2); inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; simple_inode_init_ts(inode); inode->i_blocks = 0; inode->i_generation = 0; set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags); if (!root) { set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); inode->i_flags |= S_AUTOMOUNT; } inode->i_flags |= S_NOATIME; unlock_new_inode(inode); _leave(" = %p", inode); return inode; } /* * Probe to see if a cell may exist. This prevents positive dentries from * being created unnecessarily. */ static int afs_probe_cell_name(struct dentry *dentry) { struct afs_cell *cell; struct afs_net *net = afs_d2net(dentry); const char *name = dentry->d_name.name; size_t len = dentry->d_name.len; char *result = NULL; int ret; /* Names prefixed with a dot are R/W mounts. */ if (name[0] == '.') { if (len == 1) return -EINVAL; name++; len--; } cell = afs_find_cell(net, name, len, afs_cell_trace_use_probe); if (!IS_ERR(cell)) { afs_unuse_cell(net, cell, afs_cell_trace_unuse_probe); return 0; } ret = dns_query(net->net, "afsdb", name, len, "srv=1", &result, NULL, false); if (ret == -ENODATA || ret == -ENOKEY || ret == 0) ret = -ENOENT; if (ret > 0 && ret >= sizeof(struct dns_server_list_v1_header)) { struct dns_server_list_v1_header *v1 = (void *)result; if (v1->hdr.zero == 0 && v1->hdr.content == DNS_PAYLOAD_IS_SERVER_LIST && v1->hdr.version == 1 && (v1->status != DNS_LOOKUP_GOOD && v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) return -ENOENT; } kfree(result); return ret; } /* * Try to auto mount the mountpoint with pseudo directory, if the autocell * operation is setted. */ struct inode *afs_try_auto_mntpt(struct dentry *dentry, struct inode *dir) { struct afs_vnode *vnode = AFS_FS_I(dir); struct inode *inode; int ret = -ENOENT; _enter("%p{%pd}, {%llx:%llu}", dentry, dentry, vnode->fid.vid, vnode->fid.vnode); if (!test_bit(AFS_VNODE_AUTOCELL, &vnode->flags)) goto out; ret = afs_probe_cell_name(dentry); if (ret < 0) goto out; inode = afs_iget_pseudo_dir(dir->i_sb, false); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto out; } _leave("= %p", inode); return inode; out: _leave("= %d", ret); return ret == -ENOENT ? NULL : ERR_PTR(ret); } /* * Look up @cell in a dynroot directory. This is a substitution for the * local cell name for the net namespace. */ static struct dentry *afs_lookup_atcell(struct dentry *dentry) { struct afs_cell *cell; struct afs_net *net = afs_d2net(dentry); struct dentry *ret; char *name; int len; if (!net->ws_cell) return ERR_PTR(-ENOENT); ret = ERR_PTR(-ENOMEM); name = kmalloc(AFS_MAXCELLNAME + 1, GFP_KERNEL); if (!name) goto out_p; down_read(&net->cells_lock); cell = net->ws_cell; if (cell) { len = cell->name_len; memcpy(name, cell->name, len + 1); } up_read(&net->cells_lock); ret = ERR_PTR(-ENOENT); if (!cell) goto out_n; ret = lookup_one_len(name, dentry->d_parent, len); /* We don't want to d_add() the @cell dentry here as we don't want to * the cached dentry to hide changes to the local cell name. */ out_n: kfree(name); out_p: return ret; } /* * Look up an entry in a dynroot directory. */ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { _enter("%pd", dentry); ASSERTCMP(d_inode(dentry), ==, NULL); if (flags & LOOKUP_CREATE) return ERR_PTR(-EOPNOTSUPP); if (dentry->d_name.len >= AFSNAMEMAX) { _leave(" = -ENAMETOOLONG"); return ERR_PTR(-ENAMETOOLONG); } if (dentry->d_name.len == 5 && memcmp(dentry->d_name.name, "@cell", 5) == 0) return afs_lookup_atcell(dentry); return d_splice_alias(afs_try_auto_mntpt(dentry, dir), dentry); } const struct inode_operations afs_dynroot_inode_operations = { .lookup = afs_dynroot_lookup, }; const struct dentry_operations afs_dynroot_dentry_operations = { .d_delete = always_delete_dentry, .d_release = afs_d_release, .d_automount = afs_d_automount, }; /* * Create a manually added cell mount directory. * - The caller must hold net->proc_cells_lock */ int afs_dynroot_mkdir(struct afs_net *net, struct afs_cell *cell) { struct super_block *sb = net->dynroot_sb; struct dentry *root, *subdir; int ret; if (!sb || atomic_read(&sb->s_active) == 0) return 0; /* Let the ->lookup op do the creation */ root = sb->s_root; inode_lock(root->d_inode); subdir = lookup_one_len(cell->name, root, cell->name_len); if (IS_ERR(subdir)) { ret = PTR_ERR(subdir); goto unlock; } /* Note that we're retaining an extra ref on the dentry */ subdir->d_fsdata = (void *)1UL; ret = 0; unlock: inode_unlock(root->d_inode); return ret; } /* * Remove a manually added cell mount directory. * - The caller must hold net->proc_cells_lock */ void afs_dynroot_rmdir(struct afs_net *net, struct afs_cell *cell) { struct super_block *sb = net->dynroot_sb; struct dentry *root, *subdir; if (!sb || atomic_read(&sb->s_active) == 0) return; root = sb->s_root; inode_lock(root->d_inode); /* Don't want to trigger a lookup call, which will re-add the cell */ subdir = try_lookup_one_len(cell->name, root, cell->name_len); if (IS_ERR_OR_NULL(subdir)) { _debug("lookup %ld", PTR_ERR(subdir)); goto no_dentry; } _debug("rmdir %pd %u", subdir, d_count(subdir)); if (subdir->d_fsdata) { _debug("unpin %u", d_count(subdir)); subdir->d_fsdata = NULL; dput(subdir); } dput(subdir); no_dentry: inode_unlock(root->d_inode); _leave(""); } /* * Populate a newly created dynamic root with cell names. */ int afs_dynroot_populate(struct super_block *sb) { struct afs_cell *cell; struct afs_net *net = afs_sb2net(sb); int ret; mutex_lock(&net->proc_cells_lock); net->dynroot_sb = sb; hlist_for_each_entry(cell, &net->proc_cells, proc_link) { ret = afs_dynroot_mkdir(net, cell); if (ret < 0) goto error; } ret = 0; out: mutex_unlock(&net->proc_cells_lock); return ret; error: net->dynroot_sb = NULL; goto out; } /* * When a dynamic root that's in the process of being destroyed, depopulate it * of pinned directories. */ void afs_dynroot_depopulate(struct super_block *sb) { struct afs_net *net = afs_sb2net(sb); struct dentry *root = sb->s_root, *subdir; /* Prevent more subdirs from being created */ mutex_lock(&net->proc_cells_lock); if (net->dynroot_sb == sb) net->dynroot_sb = NULL; mutex_unlock(&net->proc_cells_lock); if (root) { struct hlist_node *n; inode_lock(root->d_inode); /* Remove all the pins for dirs created for manually added cells */ hlist_for_each_entry_safe(subdir, n, &root->d_children, d_sib) { if (subdir->d_fsdata) { subdir->d_fsdata = NULL; dput(subdir); } } inode_unlock(root->d_inode); } } |
| 18 13 131 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | // SPDX-License-Identifier: GPL-2.0-only /* * Unified UUID/GUID definition * * Copyright (C) 2009, 2016 Intel Corp. * Huang Ying <ying.huang@intel.com> */ #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/uuid.h> #include <linux/random.h> const guid_t guid_null; EXPORT_SYMBOL(guid_null); const uuid_t uuid_null; EXPORT_SYMBOL(uuid_null); const u8 guid_index[16] = {3,2,1,0,5,4,7,6,8,9,10,11,12,13,14,15}; const u8 uuid_index[16] = {0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15}; /** * generate_random_uuid - generate a random UUID * @uuid: where to put the generated UUID * * Random UUID interface * * Used to create a Boot ID or a filesystem UUID/GUID, but can be * useful for other kernel drivers. */ void generate_random_uuid(unsigned char uuid[16]) { get_random_bytes(uuid, 16); /* Set UUID version to 4 --- truly random generation */ uuid[6] = (uuid[6] & 0x0F) | 0x40; /* Set the UUID variant to DCE */ uuid[8] = (uuid[8] & 0x3F) | 0x80; } EXPORT_SYMBOL(generate_random_uuid); void generate_random_guid(unsigned char guid[16]) { get_random_bytes(guid, 16); /* Set GUID version to 4 --- truly random generation */ guid[7] = (guid[7] & 0x0F) | 0x40; /* Set the GUID variant to DCE */ guid[8] = (guid[8] & 0x3F) | 0x80; } EXPORT_SYMBOL(generate_random_guid); static void __uuid_gen_common(__u8 b[16]) { get_random_bytes(b, 16); /* reversion 0b10 */ b[8] = (b[8] & 0x3F) | 0x80; } void guid_gen(guid_t *lu) { __uuid_gen_common(lu->b); /* version 4 : random generation */ lu->b[7] = (lu->b[7] & 0x0F) | 0x40; } EXPORT_SYMBOL_GPL(guid_gen); void uuid_gen(uuid_t *bu) { __uuid_gen_common(bu->b); /* version 4 : random generation */ bu->b[6] = (bu->b[6] & 0x0F) | 0x40; } EXPORT_SYMBOL_GPL(uuid_gen); /** * uuid_is_valid - checks if a UUID string is valid * @uuid: UUID string to check * * Description: * It checks if the UUID string is following the format: * xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx * * where x is a hex digit. * * Return: true if input is valid UUID string. */ bool uuid_is_valid(const char *uuid) { unsigned int i; for (i = 0; i < UUID_STRING_LEN; i++) { if (i == 8 || i == 13 || i == 18 || i == 23) { if (uuid[i] != '-') return false; } else if (!isxdigit(uuid[i])) { return false; } } return true; } EXPORT_SYMBOL(uuid_is_valid); static int __uuid_parse(const char *uuid, __u8 b[16], const u8 ei[16]) { static const u8 si[16] = {0,2,4,6,9,11,14,16,19,21,24,26,28,30,32,34}; unsigned int i; if (!uuid_is_valid(uuid)) return -EINVAL; for (i = 0; i < 16; i++) { int hi = hex_to_bin(uuid[si[i] + 0]); int lo = hex_to_bin(uuid[si[i] + 1]); b[ei[i]] = (hi << 4) | lo; } return 0; } int guid_parse(const char *uuid, guid_t *u) { return __uuid_parse(uuid, u->b, guid_index); } EXPORT_SYMBOL(guid_parse); int uuid_parse(const char *uuid, uuid_t *u) { return __uuid_parse(uuid, u->b, uuid_index); } EXPORT_SYMBOL(uuid_parse); |
| 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 #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/mmzone.h> #include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/percpu.h> #include <linux/seq_file.h> #include <linux/swap.h> #include <linux/vmstat.h> #include <linux/atomic.h> #include <linux/vmalloc.h> #ifdef CONFIG_CMA #include <linux/cma.h> #endif #include <linux/zswap.h> #include <asm/page.h> #include "internal.h" void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) { } static void show_val_kb(struct seq_file *m, const char *s, unsigned long num) { seq_put_decimal_ull_width(m, s, num << (PAGE_SHIFT - 10), 8); seq_write(m, " kB\n", 4); } static int meminfo_proc_show(struct seq_file *m, void *v) { struct sysinfo i; unsigned long committed; long cached; long available; unsigned long pages[NR_LRU_LISTS]; unsigned long sreclaimable, sunreclaim; int lru; si_meminfo(&i); si_swapinfo(&i); committed = vm_memory_committed(); cached = global_node_page_state(NR_FILE_PAGES) - total_swapcache_pages() - i.bufferram; if (cached < 0) cached = 0; for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) pages[lru] = global_node_page_state(NR_LRU_BASE + lru); available = si_mem_available(); sreclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B); sunreclaim = global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B); show_val_kb(m, "MemTotal: ", i.totalram); show_val_kb(m, "MemFree: ", i.freeram); show_val_kb(m, "MemAvailable: ", available); show_val_kb(m, "Buffers: ", i.bufferram); show_val_kb(m, "Cached: ", cached); show_val_kb(m, "SwapCached: ", total_swapcache_pages()); show_val_kb(m, "Active: ", pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]); show_val_kb(m, "Inactive: ", pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]); show_val_kb(m, "Active(anon): ", pages[LRU_ACTIVE_ANON]); show_val_kb(m, "Inactive(anon): ", pages[LRU_INACTIVE_ANON]); show_val_kb(m, "Active(file): ", pages[LRU_ACTIVE_FILE]); show_val_kb(m, "Inactive(file): ", pages[LRU_INACTIVE_FILE]); show_val_kb(m, "Unevictable: ", pages[LRU_UNEVICTABLE]); show_val_kb(m, "Mlocked: ", global_zone_page_state(NR_MLOCK)); #ifdef CONFIG_HIGHMEM show_val_kb(m, "HighTotal: ", i.totalhigh); show_val_kb(m, "HighFree: ", i.freehigh); show_val_kb(m, "LowTotal: ", i.totalram - i.totalhigh); show_val_kb(m, "LowFree: ", i.freeram - i.freehigh); #endif #ifndef CONFIG_MMU show_val_kb(m, "MmapCopy: ", (unsigned long)atomic_long_read(&mmap_pages_allocated)); #endif show_val_kb(m, "SwapTotal: ", i.totalswap); show_val_kb(m, "SwapFree: ", i.freeswap); #ifdef CONFIG_ZSWAP show_val_kb(m, "Zswap: ", zswap_total_pages()); seq_printf(m, "Zswapped: %8lu kB\n", (unsigned long)atomic_read(&zswap_stored_pages) << (PAGE_SHIFT - 10)); #endif show_val_kb(m, "Dirty: ", global_node_page_state(NR_FILE_DIRTY)); show_val_kb(m, "Writeback: ", global_node_page_state(NR_WRITEBACK)); show_val_kb(m, "AnonPages: ", global_node_page_state(NR_ANON_MAPPED)); show_val_kb(m, "Mapped: ", global_node_page_state(NR_FILE_MAPPED)); show_val_kb(m, "Shmem: ", i.sharedram); show_val_kb(m, "KReclaimable: ", sreclaimable + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE)); show_val_kb(m, "Slab: ", sreclaimable + sunreclaim); show_val_kb(m, "SReclaimable: ", sreclaimable); show_val_kb(m, "SUnreclaim: ", sunreclaim); seq_printf(m, "KernelStack: %8lu kB\n", global_node_page_state(NR_KERNEL_STACK_KB)); #ifdef CONFIG_SHADOW_CALL_STACK seq_printf(m, "ShadowCallStack:%8lu kB\n", global_node_page_state(NR_KERNEL_SCS_KB)); #endif show_val_kb(m, "PageTables: ", global_node_page_state(NR_PAGETABLE)); show_val_kb(m, "SecPageTables: ", global_node_page_state(NR_SECONDARY_PAGETABLE)); show_val_kb(m, "NFS_Unstable: ", 0); show_val_kb(m, "Bounce: ", global_zone_page_state(NR_BOUNCE)); show_val_kb(m, "WritebackTmp: ", global_node_page_state(NR_WRITEBACK_TEMP)); show_val_kb(m, "CommitLimit: ", vm_commit_limit()); show_val_kb(m, "Committed_AS: ", committed); seq_printf(m, "VmallocTotal: %8lu kB\n", (unsigned long)VMALLOC_TOTAL >> 10); show_val_kb(m, "VmallocUsed: ", vmalloc_nr_pages()); show_val_kb(m, "VmallocChunk: ", 0ul); show_val_kb(m, "Percpu: ", pcpu_nr_pages()); memtest_report_meminfo(m); #ifdef CONFIG_MEMORY_FAILURE seq_printf(m, "HardwareCorrupted: %5lu kB\n", atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)); #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE show_val_kb(m, "AnonHugePages: ", global_node_page_state(NR_ANON_THPS)); show_val_kb(m, "ShmemHugePages: ", global_node_page_state(NR_SHMEM_THPS)); show_val_kb(m, "ShmemPmdMapped: ", global_node_page_state(NR_SHMEM_PMDMAPPED)); show_val_kb(m, "FileHugePages: ", global_node_page_state(NR_FILE_THPS)); show_val_kb(m, "FilePmdMapped: ", global_node_page_state(NR_FILE_PMDMAPPED)); #endif #ifdef CONFIG_CMA show_val_kb(m, "CmaTotal: ", totalcma_pages); show_val_kb(m, "CmaFree: ", global_zone_page_state(NR_FREE_CMA_PAGES)); #endif #ifdef CONFIG_UNACCEPTED_MEMORY show_val_kb(m, "Unaccepted: ", global_zone_page_state(NR_UNACCEPTED)); #endif hugetlb_report_meminfo(m); arch_report_meminfo(m); return 0; } static int __init proc_meminfo_init(void) { struct proc_dir_entry *pde; pde = proc_create_single("meminfo", 0, NULL, meminfo_proc_show); pde_make_permanent(pde); return 0; } fs_initcall(proc_meminfo_init); |
| 2 51 53 53 51 1 1 3 1 48 48 42 6 48 48 47 1 47 1 7 48 2 2 43 1 43 1 5 39 11 11 10 7 10 4 10 7 7 1 7 3 1 2 26 5 26 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 | /* * linux/fs/hfs/mdb.c * * Copyright (C) 1995-1997 Paul H. Hargrove * (C) 2003 Ardis Technologies <roman@ardistech.com> * This file may be distributed under the terms of the GNU General Public License. * * This file contains functions for reading/writing the MDB. */ #include <linux/cdrom.h> #include <linux/blkdev.h> #include <linux/nls.h> #include <linux/slab.h> #include "hfs_fs.h" #include "btree.h" /*================ File-local data types ================*/ /* * The HFS Master Directory Block (MDB). * * Also known as the Volume Information Block (VIB), this structure is * the HFS equivalent of a superblock. * * Reference: _Inside Macintosh: Files_ pages 2-59 through 2-62 * * modified for HFS Extended */ static int hfs_get_last_session(struct super_block *sb, sector_t *start, sector_t *size) { struct cdrom_device_info *cdi = disk_to_cdi(sb->s_bdev->bd_disk); /* default values */ *start = 0; *size = bdev_nr_sectors(sb->s_bdev); if (HFS_SB(sb)->session >= 0) { struct cdrom_tocentry te; if (!cdi) return -EINVAL; te.cdte_track = HFS_SB(sb)->session; te.cdte_format = CDROM_LBA; if (cdrom_read_tocentry(cdi, &te) || (te.cdte_ctrl & CDROM_DATA_TRACK) != 4) { pr_err("invalid session number or type of track\n"); return -EINVAL; } *start = (sector_t)te.cdte_addr.lba << 2; } else if (cdi) { struct cdrom_multisession ms_info; ms_info.addr_format = CDROM_LBA; if (cdrom_multisession(cdi, &ms_info) == 0 && ms_info.xa_flag) *start = (sector_t)ms_info.addr.lba << 2; } return 0; } /* * hfs_mdb_get() * * Build the in-core MDB for a filesystem, including * the B-trees and the volume bitmap. */ int hfs_mdb_get(struct super_block *sb) { struct buffer_head *bh; struct hfs_mdb *mdb, *mdb2; unsigned int block; char *ptr; int off2, len, size, sect; sector_t part_start, part_size; loff_t off; __be16 attrib; /* set the device driver to 512-byte blocks */ size = sb_min_blocksize(sb, HFS_SECTOR_SIZE); if (!size) return -EINVAL; if (hfs_get_last_session(sb, &part_start, &part_size)) return -EINVAL; while (1) { /* See if this is an HFS filesystem */ bh = sb_bread512(sb, part_start + HFS_MDB_BLK, mdb); if (!bh) goto out; if (mdb->drSigWord == cpu_to_be16(HFS_SUPER_MAGIC)) break; brelse(bh); /* check for a partition block * (should do this only for cdrom/loop though) */ if (hfs_part_find(sb, &part_start, &part_size)) goto out; } HFS_SB(sb)->alloc_blksz = size = be32_to_cpu(mdb->drAlBlkSiz); if (!size || (size & (HFS_SECTOR_SIZE - 1))) { pr_err("bad allocation block size %d\n", size); goto out_bh; } size = min(HFS_SB(sb)->alloc_blksz, (u32)PAGE_SIZE); /* size must be a multiple of 512 */ while (size & (size - 1)) size -= HFS_SECTOR_SIZE; sect = be16_to_cpu(mdb->drAlBlSt) + part_start; /* align block size to first sector */ while (sect & ((size - 1) >> HFS_SECTOR_SIZE_BITS)) size >>= 1; /* align block size to weird alloc size */ while (HFS_SB(sb)->alloc_blksz & (size - 1)) size >>= 1; brelse(bh); if (!sb_set_blocksize(sb, size)) { pr_err("unable to set blocksize to %u\n", size); goto out; } bh = sb_bread512(sb, part_start + HFS_MDB_BLK, mdb); if (!bh) goto out; if (mdb->drSigWord != cpu_to_be16(HFS_SUPER_MAGIC)) goto out_bh; HFS_SB(sb)->mdb_bh = bh; HFS_SB(sb)->mdb = mdb; /* These parameters are read from the MDB, and never written */ HFS_SB(sb)->part_start = part_start; HFS_SB(sb)->fs_ablocks = be16_to_cpu(mdb->drNmAlBlks); HFS_SB(sb)->fs_div = HFS_SB(sb)->alloc_blksz >> sb->s_blocksize_bits; HFS_SB(sb)->clumpablks = be32_to_cpu(mdb->drClpSiz) / HFS_SB(sb)->alloc_blksz; if (!HFS_SB(sb)->clumpablks) HFS_SB(sb)->clumpablks = 1; HFS_SB(sb)->fs_start = (be16_to_cpu(mdb->drAlBlSt) + part_start) >> (sb->s_blocksize_bits - HFS_SECTOR_SIZE_BITS); /* These parameters are read from and written to the MDB */ HFS_SB(sb)->free_ablocks = be16_to_cpu(mdb->drFreeBks); HFS_SB(sb)->next_id = be32_to_cpu(mdb->drNxtCNID); HFS_SB(sb)->root_files = be16_to_cpu(mdb->drNmFls); HFS_SB(sb)->root_dirs = be16_to_cpu(mdb->drNmRtDirs); HFS_SB(sb)->file_count = be32_to_cpu(mdb->drFilCnt); HFS_SB(sb)->folder_count = be32_to_cpu(mdb->drDirCnt); /* TRY to get the alternate (backup) MDB. */ sect = part_start + part_size - 2; bh = sb_bread512(sb, sect, mdb2); if (bh) { if (mdb2->drSigWord == cpu_to_be16(HFS_SUPER_MAGIC)) { HFS_SB(sb)->alt_mdb_bh = bh; HFS_SB(sb)->alt_mdb = mdb2; } else brelse(bh); } if (!HFS_SB(sb)->alt_mdb) { pr_warn("unable to locate alternate MDB\n"); pr_warn("continuing without an alternate MDB\n"); } HFS_SB(sb)->bitmap = kmalloc(8192, GFP_KERNEL); if (!HFS_SB(sb)->bitmap) goto out; /* read in the bitmap */ block = be16_to_cpu(mdb->drVBMSt) + part_start; off = (loff_t)block << HFS_SECTOR_SIZE_BITS; size = (HFS_SB(sb)->fs_ablocks + 8) / 8; ptr = (u8 *)HFS_SB(sb)->bitmap; while (size) { bh = sb_bread(sb, off >> sb->s_blocksize_bits); if (!bh) { pr_err("unable to read volume bitmap\n"); goto out; } off2 = off & (sb->s_blocksize - 1); len = min((int)sb->s_blocksize - off2, size); memcpy(ptr, bh->b_data + off2, len); brelse(bh); ptr += len; off += len; size -= len; } HFS_SB(sb)->ext_tree = hfs_btree_open(sb, HFS_EXT_CNID, hfs_ext_keycmp); if (!HFS_SB(sb)->ext_tree) { pr_err("unable to open extent tree\n"); goto out; } HFS_SB(sb)->cat_tree = hfs_btree_open(sb, HFS_CAT_CNID, hfs_cat_keycmp); if (!HFS_SB(sb)->cat_tree) { pr_err("unable to open catalog tree\n"); goto out; } attrib = mdb->drAtrb; if (!(attrib & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. mounting read-only.\n"); sb->s_flags |= SB_RDONLY; } if ((attrib & cpu_to_be16(HFS_SB_ATTRIB_SLOCK))) { pr_warn("filesystem is marked locked, mounting read-only.\n"); sb->s_flags |= SB_RDONLY; } if (!sb_rdonly(sb)) { /* Mark the volume uncleanly unmounted in case we crash */ attrib &= cpu_to_be16(~HFS_SB_ATTRIB_UNMNT); attrib |= cpu_to_be16(HFS_SB_ATTRIB_INCNSTNT); mdb->drAtrb = attrib; be32_add_cpu(&mdb->drWrCnt, 1); mdb->drLsMod = hfs_mtime(); mark_buffer_dirty(HFS_SB(sb)->mdb_bh); sync_dirty_buffer(HFS_SB(sb)->mdb_bh); } return 0; out_bh: brelse(bh); out: hfs_mdb_put(sb); return -EIO; } /* * hfs_mdb_commit() * * Description: * This updates the MDB on disk. * It does not check, if the superblock has been modified, or * if the filesystem has been mounted read-only. It is mainly * called by hfs_sync_fs() and flush_mdb(). * Input Variable(s): * struct hfs_mdb *mdb: Pointer to the hfs MDB * int backup; * Output Variable(s): * NONE * Returns: * void * Preconditions: * 'mdb' points to a "valid" (struct hfs_mdb). * Postconditions: * The HFS MDB and on disk will be updated, by copying the possibly * modified fields from the in memory MDB (in native byte order) to * the disk block buffer. * If 'backup' is non-zero then the alternate MDB is also written * and the function doesn't return until it is actually on disk. */ void hfs_mdb_commit(struct super_block *sb) { struct hfs_mdb *mdb = HFS_SB(sb)->mdb; if (sb_rdonly(sb)) return; lock_buffer(HFS_SB(sb)->mdb_bh); if (test_and_clear_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags)) { /* These parameters may have been modified, so write them back */ mdb->drLsMod = hfs_mtime(); mdb->drFreeBks = cpu_to_be16(HFS_SB(sb)->free_ablocks); mdb->drNxtCNID = cpu_to_be32(HFS_SB(sb)->next_id); mdb->drNmFls = cpu_to_be16(HFS_SB(sb)->root_files); mdb->drNmRtDirs = cpu_to_be16(HFS_SB(sb)->root_dirs); mdb->drFilCnt = cpu_to_be32(HFS_SB(sb)->file_count); mdb->drDirCnt = cpu_to_be32(HFS_SB(sb)->folder_count); /* write MDB to disk */ mark_buffer_dirty(HFS_SB(sb)->mdb_bh); } /* write the backup MDB, not returning until it is written. * we only do this when either the catalog or extents overflow * files grow. */ if (test_and_clear_bit(HFS_FLG_ALT_MDB_DIRTY, &HFS_SB(sb)->flags) && HFS_SB(sb)->alt_mdb) { hfs_inode_write_fork(HFS_SB(sb)->ext_tree->inode, mdb->drXTExtRec, &mdb->drXTFlSize, NULL); hfs_inode_write_fork(HFS_SB(sb)->cat_tree->inode, mdb->drCTExtRec, &mdb->drCTFlSize, NULL); lock_buffer(HFS_SB(sb)->alt_mdb_bh); memcpy(HFS_SB(sb)->alt_mdb, HFS_SB(sb)->mdb, HFS_SECTOR_SIZE); HFS_SB(sb)->alt_mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT); HFS_SB(sb)->alt_mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT); unlock_buffer(HFS_SB(sb)->alt_mdb_bh); mark_buffer_dirty(HFS_SB(sb)->alt_mdb_bh); sync_dirty_buffer(HFS_SB(sb)->alt_mdb_bh); } if (test_and_clear_bit(HFS_FLG_BITMAP_DIRTY, &HFS_SB(sb)->flags)) { struct buffer_head *bh; sector_t block; char *ptr; int off, size, len; block = be16_to_cpu(HFS_SB(sb)->mdb->drVBMSt) + HFS_SB(sb)->part_start; off = (block << HFS_SECTOR_SIZE_BITS) & (sb->s_blocksize - 1); block >>= sb->s_blocksize_bits - HFS_SECTOR_SIZE_BITS; size = (HFS_SB(sb)->fs_ablocks + 7) / 8; ptr = (u8 *)HFS_SB(sb)->bitmap; while (size) { bh = sb_bread(sb, block); if (!bh) { pr_err("unable to read volume bitmap\n"); break; } len = min((int)sb->s_blocksize - off, size); lock_buffer(bh); memcpy(bh->b_data + off, ptr, len); unlock_buffer(bh); mark_buffer_dirty(bh); brelse(bh); block++; off = 0; ptr += len; size -= len; } } unlock_buffer(HFS_SB(sb)->mdb_bh); } void hfs_mdb_close(struct super_block *sb) { /* update volume attributes */ if (sb_rdonly(sb)) return; HFS_SB(sb)->mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT); HFS_SB(sb)->mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT); mark_buffer_dirty(HFS_SB(sb)->mdb_bh); } /* * hfs_mdb_put() * * Release the resources associated with the in-core MDB. */ void hfs_mdb_put(struct super_block *sb) { if (!HFS_SB(sb)) return; /* free the B-trees */ hfs_btree_close(HFS_SB(sb)->ext_tree); hfs_btree_close(HFS_SB(sb)->cat_tree); /* free the buffers holding the primary and alternate MDBs */ brelse(HFS_SB(sb)->mdb_bh); brelse(HFS_SB(sb)->alt_mdb_bh); unload_nls(HFS_SB(sb)->nls_io); unload_nls(HFS_SB(sb)->nls_disk); kfree(HFS_SB(sb)->bitmap); kfree(HFS_SB(sb)); sb->s_fs_info = NULL; } |
| 5 5 5 6 1 2 3 3 2 2 3 3 2 2 3 3 2 5 5 5 22 5 1 1 1 1 1 4 1 1 2 4 1 1 2 5 1 6 2 4 15 1 1 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2008, Christoph Hellwig * All Rights Reserved. */ #include "xfs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_quota.h" #include "xfs_trans.h" #include "xfs_icache.h" #include "xfs_qm.h" static void xfs_qm_fill_state( struct qc_type_state *tstate, struct xfs_mount *mp, struct xfs_inode *ip, xfs_ino_t ino, struct xfs_def_quota *defq) { bool tempqip = false; tstate->ino = ino; if (!ip && ino == NULLFSINO) return; if (!ip) { if (xfs_iget(mp, NULL, ino, 0, 0, &ip)) return; tempqip = true; } tstate->flags |= QCI_SYSFILE; tstate->blocks = ip->i_nblocks; tstate->nextents = ip->i_df.if_nextents; tstate->spc_timelimit = (u32)defq->blk.time; tstate->ino_timelimit = (u32)defq->ino.time; tstate->rt_spc_timelimit = (u32)defq->rtb.time; tstate->spc_warnlimit = 0; tstate->ino_warnlimit = 0; tstate->rt_spc_warnlimit = 0; if (tempqip) xfs_irele(ip); } /* * Return quota status information, such as enforcements, quota file inode * numbers etc. */ static int xfs_fs_get_quota_state( struct super_block *sb, struct qc_state *state) { struct xfs_mount *mp = XFS_M(sb); struct xfs_quotainfo *q = mp->m_quotainfo; memset(state, 0, sizeof(*state)); if (!XFS_IS_QUOTA_ON(mp)) return 0; state->s_incoredqs = q->qi_dquots; if (XFS_IS_UQUOTA_ON(mp)) state->s_state[USRQUOTA].flags |= QCI_ACCT_ENABLED; if (XFS_IS_UQUOTA_ENFORCED(mp)) state->s_state[USRQUOTA].flags |= QCI_LIMITS_ENFORCED; if (XFS_IS_GQUOTA_ON(mp)) state->s_state[GRPQUOTA].flags |= QCI_ACCT_ENABLED; if (XFS_IS_GQUOTA_ENFORCED(mp)) state->s_state[GRPQUOTA].flags |= QCI_LIMITS_ENFORCED; if (XFS_IS_PQUOTA_ON(mp)) state->s_state[PRJQUOTA].flags |= QCI_ACCT_ENABLED; if (XFS_IS_PQUOTA_ENFORCED(mp)) state->s_state[PRJQUOTA].flags |= QCI_LIMITS_ENFORCED; xfs_qm_fill_state(&state->s_state[USRQUOTA], mp, q->qi_uquotaip, mp->m_sb.sb_uquotino, &q->qi_usr_default); xfs_qm_fill_state(&state->s_state[GRPQUOTA], mp, q->qi_gquotaip, mp->m_sb.sb_gquotino, &q->qi_grp_default); xfs_qm_fill_state(&state->s_state[PRJQUOTA], mp, q->qi_pquotaip, mp->m_sb.sb_pquotino, &q->qi_prj_default); return 0; } STATIC xfs_dqtype_t xfs_quota_type(int type) { switch (type) { case USRQUOTA: return XFS_DQTYPE_USER; case GRPQUOTA: return XFS_DQTYPE_GROUP; default: return XFS_DQTYPE_PROJ; } } #define XFS_QC_SETINFO_MASK (QC_TIMER_MASK) /* * Adjust quota timers & warnings */ static int xfs_fs_set_info( struct super_block *sb, int type, struct qc_info *info) { struct xfs_mount *mp = XFS_M(sb); struct qc_dqblk newlim; if (sb_rdonly(sb)) return -EROFS; if (!XFS_IS_QUOTA_ON(mp)) return -ENOSYS; if (info->i_fieldmask & ~XFS_QC_SETINFO_MASK) return -EINVAL; if ((info->i_fieldmask & XFS_QC_SETINFO_MASK) == 0) return 0; newlim.d_fieldmask = info->i_fieldmask; newlim.d_spc_timer = info->i_spc_timelimit; newlim.d_ino_timer = info->i_ino_timelimit; newlim.d_rt_spc_timer = info->i_rt_spc_timelimit; newlim.d_ino_warns = info->i_ino_warnlimit; newlim.d_spc_warns = info->i_spc_warnlimit; newlim.d_rt_spc_warns = info->i_rt_spc_warnlimit; return xfs_qm_scall_setqlim(mp, 0, xfs_quota_type(type), &newlim); } static unsigned int xfs_quota_flags(unsigned int uflags) { unsigned int flags = 0; if (uflags & FS_QUOTA_UDQ_ACCT) flags |= XFS_UQUOTA_ACCT; if (uflags & FS_QUOTA_PDQ_ACCT) flags |= XFS_PQUOTA_ACCT; if (uflags & FS_QUOTA_GDQ_ACCT) flags |= XFS_GQUOTA_ACCT; if (uflags & FS_QUOTA_UDQ_ENFD) flags |= XFS_UQUOTA_ENFD; if (uflags & FS_QUOTA_GDQ_ENFD) flags |= XFS_GQUOTA_ENFD; if (uflags & FS_QUOTA_PDQ_ENFD) flags |= XFS_PQUOTA_ENFD; return flags; } STATIC int xfs_quota_enable( struct super_block *sb, unsigned int uflags) { struct xfs_mount *mp = XFS_M(sb); if (sb_rdonly(sb)) return -EROFS; if (!XFS_IS_QUOTA_ON(mp)) return -ENOSYS; return xfs_qm_scall_quotaon(mp, xfs_quota_flags(uflags)); } STATIC int xfs_quota_disable( struct super_block *sb, unsigned int uflags) { struct xfs_mount *mp = XFS_M(sb); if (sb_rdonly(sb)) return -EROFS; if (!XFS_IS_QUOTA_ON(mp)) return -ENOSYS; return xfs_qm_scall_quotaoff(mp, xfs_quota_flags(uflags)); } STATIC int xfs_fs_rm_xquota( struct super_block *sb, unsigned int uflags) { struct xfs_mount *mp = XFS_M(sb); unsigned int flags = 0; if (sb_rdonly(sb)) return -EROFS; if (XFS_IS_QUOTA_ON(mp)) return -EINVAL; if (uflags & ~(FS_USER_QUOTA | FS_GROUP_QUOTA | FS_PROJ_QUOTA)) return -EINVAL; if (uflags & FS_USER_QUOTA) flags |= XFS_QMOPT_UQUOTA; if (uflags & FS_GROUP_QUOTA) flags |= XFS_QMOPT_GQUOTA; if (uflags & FS_PROJ_QUOTA) flags |= XFS_QMOPT_PQUOTA; return xfs_qm_scall_trunc_qfiles(mp, flags); } STATIC int xfs_fs_get_dqblk( struct super_block *sb, struct kqid qid, struct qc_dqblk *qdq) { struct xfs_mount *mp = XFS_M(sb); xfs_dqid_t id; if (!XFS_IS_QUOTA_ON(mp)) return -ENOSYS; id = from_kqid(&init_user_ns, qid); return xfs_qm_scall_getquota(mp, id, xfs_quota_type(qid.type), qdq); } /* Return quota info for active quota >= this qid */ STATIC int xfs_fs_get_nextdqblk( struct super_block *sb, struct kqid *qid, struct qc_dqblk *qdq) { int ret; struct xfs_mount *mp = XFS_M(sb); xfs_dqid_t id; if (!XFS_IS_QUOTA_ON(mp)) return -ENOSYS; id = from_kqid(&init_user_ns, *qid); ret = xfs_qm_scall_getquota_next(mp, &id, xfs_quota_type(qid->type), qdq); if (ret) return ret; /* ID may be different, so convert back what we got */ *qid = make_kqid(current_user_ns(), qid->type, id); return 0; } STATIC int xfs_fs_set_dqblk( struct super_block *sb, struct kqid qid, struct qc_dqblk *qdq) { struct xfs_mount *mp = XFS_M(sb); if (sb_rdonly(sb)) return -EROFS; if (!XFS_IS_QUOTA_ON(mp)) return -ENOSYS; return xfs_qm_scall_setqlim(mp, from_kqid(&init_user_ns, qid), xfs_quota_type(qid.type), qdq); } const struct quotactl_ops xfs_quotactl_operations = { .get_state = xfs_fs_get_quota_state, .set_info = xfs_fs_set_info, .quota_enable = xfs_quota_enable, .quota_disable = xfs_quota_disable, .rm_xquota = xfs_fs_rm_xquota, .get_dqblk = xfs_fs_get_dqblk, .get_nextdqblk = xfs_fs_get_nextdqblk, .set_dqblk = xfs_fs_set_dqblk, }; |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2004, 2005 Oracle. All rights reserved. */ #include <linux/slab.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/configfs.h> #include "tcp.h" #include "nodemanager.h" #include "heartbeat.h" #include "masklog.h" #include "sys.h" /* for now we operate under the assertion that there can be only one * cluster active at a time. Changing this will require trickling * cluster references throughout where nodes are looked up */ struct o2nm_cluster *o2nm_single_cluster = NULL; static const char *o2nm_fence_method_desc[O2NM_FENCE_METHODS] = { "reset", /* O2NM_FENCE_RESET */ "panic", /* O2NM_FENCE_PANIC */ }; static inline void o2nm_lock_subsystem(void); static inline void o2nm_unlock_subsystem(void); struct o2nm_node *o2nm_get_node_by_num(u8 node_num) { struct o2nm_node *node = NULL; if (node_num >= O2NM_MAX_NODES || o2nm_single_cluster == NULL) goto out; read_lock(&o2nm_single_cluster->cl_nodes_lock); node = o2nm_single_cluster->cl_nodes[node_num]; if (node) config_item_get(&node->nd_item); read_unlock(&o2nm_single_cluster->cl_nodes_lock); out: return node; } EXPORT_SYMBOL_GPL(o2nm_get_node_by_num); int o2nm_configured_node_map(unsigned long *map, unsigned bytes) { struct o2nm_cluster *cluster = o2nm_single_cluster; BUG_ON(bytes < (sizeof(cluster->cl_nodes_bitmap))); if (cluster == NULL) return -EINVAL; read_lock(&cluster->cl_nodes_lock); bitmap_copy(map, cluster->cl_nodes_bitmap, O2NM_MAX_NODES); read_unlock(&cluster->cl_nodes_lock); return 0; } EXPORT_SYMBOL_GPL(o2nm_configured_node_map); static struct o2nm_node *o2nm_node_ip_tree_lookup(struct o2nm_cluster *cluster, __be32 ip_needle, struct rb_node ***ret_p, struct rb_node **ret_parent) { struct rb_node **p = &cluster->cl_node_ip_tree.rb_node; struct rb_node *parent = NULL; struct o2nm_node *node, *ret = NULL; while (*p) { int cmp; parent = *p; node = rb_entry(parent, struct o2nm_node, nd_ip_node); cmp = memcmp(&ip_needle, &node->nd_ipv4_address, sizeof(ip_needle)); if (cmp < 0) p = &(*p)->rb_left; else if (cmp > 0) p = &(*p)->rb_right; else { ret = node; break; } } if (ret_p != NULL) *ret_p = p; if (ret_parent != NULL) *ret_parent = parent; return ret; } struct o2nm_node *o2nm_get_node_by_ip(__be32 addr) { struct o2nm_node *node = NULL; struct o2nm_cluster *cluster = o2nm_single_cluster; if (cluster == NULL) goto out; read_lock(&cluster->cl_nodes_lock); node = o2nm_node_ip_tree_lookup(cluster, addr, NULL, NULL); if (node) config_item_get(&node->nd_item); read_unlock(&cluster->cl_nodes_lock); out: return node; } EXPORT_SYMBOL_GPL(o2nm_get_node_by_ip); void o2nm_node_put(struct o2nm_node *node) { config_item_put(&node->nd_item); } EXPORT_SYMBOL_GPL(o2nm_node_put); void o2nm_node_get(struct o2nm_node *node) { config_item_get(&node->nd_item); } EXPORT_SYMBOL_GPL(o2nm_node_get); u8 o2nm_this_node(void) { u8 node_num = O2NM_MAX_NODES; if (o2nm_single_cluster && o2nm_single_cluster->cl_has_local) node_num = o2nm_single_cluster->cl_local_node; return node_num; } EXPORT_SYMBOL_GPL(o2nm_this_node); /* node configfs bits */ static struct o2nm_cluster *to_o2nm_cluster(struct config_item *item) { return item ? container_of(to_config_group(item), struct o2nm_cluster, cl_group) : NULL; } static struct o2nm_node *to_o2nm_node(struct config_item *item) { return item ? container_of(item, struct o2nm_node, nd_item) : NULL; } static void o2nm_node_release(struct config_item *item) { struct o2nm_node *node = to_o2nm_node(item); kfree(node); } static ssize_t o2nm_node_num_show(struct config_item *item, char *page) { return sprintf(page, "%d\n", to_o2nm_node(item)->nd_num); } static struct o2nm_cluster *to_o2nm_cluster_from_node(struct o2nm_node *node) { /* through the first node_set .parent * mycluster/nodes/mynode == o2nm_cluster->o2nm_node_group->o2nm_node */ if (node->nd_item.ci_parent) return to_o2nm_cluster(node->nd_item.ci_parent->ci_parent); else return NULL; } enum { O2NM_NODE_ATTR_NUM = 0, O2NM_NODE_ATTR_PORT, O2NM_NODE_ATTR_ADDRESS, }; static ssize_t o2nm_node_num_store(struct config_item *item, const char *page, size_t count) { struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster; unsigned long tmp; char *p = (char *)page; int ret = 0; tmp = simple_strtoul(p, &p, 0); if (!p || (*p && (*p != '\n'))) return -EINVAL; if (tmp >= O2NM_MAX_NODES) return -ERANGE; /* once we're in the cl_nodes tree networking can look us up by * node number and try to use our address and port attributes * to connect to this node.. make sure that they've been set * before writing the node attribute? */ if (!test_bit(O2NM_NODE_ATTR_ADDRESS, &node->nd_set_attributes) || !test_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes)) return -EINVAL; /* XXX */ o2nm_lock_subsystem(); cluster = to_o2nm_cluster_from_node(node); if (!cluster) { o2nm_unlock_subsystem(); return -EINVAL; } write_lock(&cluster->cl_nodes_lock); if (cluster->cl_nodes[tmp]) ret = -EEXIST; else if (test_and_set_bit(O2NM_NODE_ATTR_NUM, &node->nd_set_attributes)) ret = -EBUSY; else { cluster->cl_nodes[tmp] = node; node->nd_num = tmp; set_bit(tmp, cluster->cl_nodes_bitmap); } write_unlock(&cluster->cl_nodes_lock); o2nm_unlock_subsystem(); if (ret) return ret; return count; } static ssize_t o2nm_node_ipv4_port_show(struct config_item *item, char *page) { return sprintf(page, "%u\n", ntohs(to_o2nm_node(item)->nd_ipv4_port)); } static ssize_t o2nm_node_ipv4_port_store(struct config_item *item, const char *page, size_t count) { struct o2nm_node *node = to_o2nm_node(item); unsigned long tmp; char *p = (char *)page; tmp = simple_strtoul(p, &p, 0); if (!p || (*p && (*p != '\n'))) return -EINVAL; if (tmp == 0) return -EINVAL; if (tmp >= (u16)-1) return -ERANGE; if (test_and_set_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes)) return -EBUSY; node->nd_ipv4_port = htons(tmp); return count; } static ssize_t o2nm_node_ipv4_address_show(struct config_item *item, char *page) { return sprintf(page, "%pI4\n", &to_o2nm_node(item)->nd_ipv4_address); } static ssize_t o2nm_node_ipv4_address_store(struct config_item *item, const char *page, size_t count) { struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster; int ret, i; struct rb_node **p, *parent; unsigned int octets[4]; __be32 ipv4_addr = 0; ret = sscanf(page, "%3u.%3u.%3u.%3u", &octets[3], &octets[2], &octets[1], &octets[0]); if (ret != 4) return -EINVAL; for (i = 0; i < ARRAY_SIZE(octets); i++) { if (octets[i] > 255) return -ERANGE; be32_add_cpu(&ipv4_addr, octets[i] << (i * 8)); } o2nm_lock_subsystem(); cluster = to_o2nm_cluster_from_node(node); if (!cluster) { o2nm_unlock_subsystem(); return -EINVAL; } ret = 0; write_lock(&cluster->cl_nodes_lock); if (o2nm_node_ip_tree_lookup(cluster, ipv4_addr, &p, &parent)) ret = -EEXIST; else if (test_and_set_bit(O2NM_NODE_ATTR_ADDRESS, &node->nd_set_attributes)) ret = -EBUSY; else { rb_link_node(&node->nd_ip_node, parent, p); rb_insert_color(&node->nd_ip_node, &cluster->cl_node_ip_tree); } write_unlock(&cluster->cl_nodes_lock); o2nm_unlock_subsystem(); if (ret) return ret; memcpy(&node->nd_ipv4_address, &ipv4_addr, sizeof(ipv4_addr)); return count; } static ssize_t o2nm_node_local_show(struct config_item *item, char *page) { return sprintf(page, "%d\n", to_o2nm_node(item)->nd_local); } static ssize_t o2nm_node_local_store(struct config_item *item, const char *page, size_t count) { struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster; unsigned long tmp; char *p = (char *)page; ssize_t ret; tmp = simple_strtoul(p, &p, 0); if (!p || (*p && (*p != '\n'))) return -EINVAL; tmp = !!tmp; /* boolean of whether this node wants to be local */ /* setting local turns on networking rx for now so we require having * set everything else first */ if (!test_bit(O2NM_NODE_ATTR_ADDRESS, &node->nd_set_attributes) || !test_bit(O2NM_NODE_ATTR_NUM, &node->nd_set_attributes) || !test_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes)) return -EINVAL; /* XXX */ o2nm_lock_subsystem(); cluster = to_o2nm_cluster_from_node(node); if (!cluster) { ret = -EINVAL; goto out; } /* the only failure case is trying to set a new local node * when a different one is already set */ if (tmp && tmp == cluster->cl_has_local && cluster->cl_local_node != node->nd_num) { ret = -EBUSY; goto out; } /* bring up the rx thread if we're setting the new local node. */ if (tmp && !cluster->cl_has_local) { ret = o2net_start_listening(node); if (ret) goto out; } if (!tmp && cluster->cl_has_local && cluster->cl_local_node == node->nd_num) { o2net_stop_listening(node); cluster->cl_local_node = O2NM_INVALID_NODE_NUM; } node->nd_local = tmp; if (node->nd_local) { cluster->cl_has_local = tmp; cluster->cl_local_node = node->nd_num; } ret = count; out: o2nm_unlock_subsystem(); return ret; } CONFIGFS_ATTR(o2nm_node_, num); CONFIGFS_ATTR(o2nm_node_, ipv4_port); CONFIGFS_ATTR(o2nm_node_, ipv4_address); CONFIGFS_ATTR(o2nm_node_, local); static struct configfs_attribute *o2nm_node_attrs[] = { &o2nm_node_attr_num, &o2nm_node_attr_ipv4_port, &o2nm_node_attr_ipv4_address, &o2nm_node_attr_local, NULL, }; static struct configfs_item_operations o2nm_node_item_ops = { .release = o2nm_node_release, }; static const struct config_item_type o2nm_node_type = { .ct_item_ops = &o2nm_node_item_ops, .ct_attrs = o2nm_node_attrs, .ct_owner = THIS_MODULE, }; /* node set */ struct o2nm_node_group { struct config_group ns_group; /* some stuff? */ }; #if 0 static struct o2nm_node_group *to_o2nm_node_group(struct config_group *group) { return group ? container_of(group, struct o2nm_node_group, ns_group) : NULL; } #endif static ssize_t o2nm_cluster_attr_write(const char *page, ssize_t count, unsigned int *val) { unsigned long tmp; char *p = (char *)page; tmp = simple_strtoul(p, &p, 0); if (!p || (*p && (*p != '\n'))) return -EINVAL; if (tmp == 0) return -EINVAL; if (tmp >= (u32)-1) return -ERANGE; *val = tmp; return count; } static ssize_t o2nm_cluster_idle_timeout_ms_show(struct config_item *item, char *page) { return sprintf(page, "%u\n", to_o2nm_cluster(item)->cl_idle_timeout_ms); } static ssize_t o2nm_cluster_idle_timeout_ms_store(struct config_item *item, const char *page, size_t count) { struct o2nm_cluster *cluster = to_o2nm_cluster(item); ssize_t ret; unsigned int val; ret = o2nm_cluster_attr_write(page, count, &val); if (ret > 0) { if (cluster->cl_idle_timeout_ms != val && o2net_num_connected_peers()) { mlog(ML_NOTICE, "o2net: cannot change idle timeout after " "the first peer has agreed to it." " %d connected peers\n", o2net_num_connected_peers()); ret = -EINVAL; } else if (val <= cluster->cl_keepalive_delay_ms) { mlog(ML_NOTICE, "o2net: idle timeout must be larger " "than keepalive delay\n"); ret = -EINVAL; } else { cluster->cl_idle_timeout_ms = val; } } return ret; } static ssize_t o2nm_cluster_keepalive_delay_ms_show( struct config_item *item, char *page) { return sprintf(page, "%u\n", to_o2nm_cluster(item)->cl_keepalive_delay_ms); } static ssize_t o2nm_cluster_keepalive_delay_ms_store( struct config_item *item, const char *page, size_t count) { struct o2nm_cluster *cluster = to_o2nm_cluster(item); ssize_t ret; unsigned int val; ret = o2nm_cluster_attr_write(page, count, &val); if (ret > 0) { if (cluster->cl_keepalive_delay_ms != val && o2net_num_connected_peers()) { mlog(ML_NOTICE, "o2net: cannot change keepalive delay after" " the first peer has agreed to it." " %d connected peers\n", o2net_num_connected_peers()); ret = -EINVAL; } else if (val >= cluster->cl_idle_timeout_ms) { mlog(ML_NOTICE, "o2net: keepalive delay must be " "smaller than idle timeout\n"); ret = -EINVAL; } else { cluster->cl_keepalive_delay_ms = val; } } return ret; } static ssize_t o2nm_cluster_reconnect_delay_ms_show( struct config_item *item, char *page) { return sprintf(page, "%u\n", to_o2nm_cluster(item)->cl_reconnect_delay_ms); } static ssize_t o2nm_cluster_reconnect_delay_ms_store( struct config_item *item, const char *page, size_t count) { return o2nm_cluster_attr_write(page, count, &to_o2nm_cluster(item)->cl_reconnect_delay_ms); } static ssize_t o2nm_cluster_fence_method_show( struct config_item *item, char *page) { struct o2nm_cluster *cluster = to_o2nm_cluster(item); ssize_t ret = 0; if (cluster) ret = sprintf(page, "%s\n", o2nm_fence_method_desc[cluster->cl_fence_method]); return ret; } static ssize_t o2nm_cluster_fence_method_store( struct config_item *item, const char *page, size_t count) { unsigned int i; if (page[count - 1] != '\n') goto bail; for (i = 0; i < O2NM_FENCE_METHODS; ++i) { if (count != strlen(o2nm_fence_method_desc[i]) + 1) continue; if (strncasecmp(page, o2nm_fence_method_desc[i], count - 1)) continue; if (to_o2nm_cluster(item)->cl_fence_method != i) { printk(KERN_INFO "ocfs2: Changing fence method to %s\n", o2nm_fence_method_desc[i]); to_o2nm_cluster(item)->cl_fence_method = i; } return count; } bail: return -EINVAL; } CONFIGFS_ATTR(o2nm_cluster_, idle_timeout_ms); CONFIGFS_ATTR(o2nm_cluster_, keepalive_delay_ms); CONFIGFS_ATTR(o2nm_cluster_, reconnect_delay_ms); CONFIGFS_ATTR(o2nm_cluster_, fence_method); static struct configfs_attribute *o2nm_cluster_attrs[] = { &o2nm_cluster_attr_idle_timeout_ms, &o2nm_cluster_attr_keepalive_delay_ms, &o2nm_cluster_attr_reconnect_delay_ms, &o2nm_cluster_attr_fence_method, NULL, }; static struct config_item *o2nm_node_group_make_item(struct config_group *group, const char *name) { struct o2nm_node *node = NULL; if (strlen(name) > O2NM_MAX_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); node = kzalloc(sizeof(struct o2nm_node), GFP_KERNEL); if (node == NULL) return ERR_PTR(-ENOMEM); strcpy(node->nd_name, name); /* use item.ci_namebuf instead? */ config_item_init_type_name(&node->nd_item, name, &o2nm_node_type); spin_lock_init(&node->nd_lock); mlog(ML_CLUSTER, "o2nm: Registering node %s\n", name); return &node->nd_item; } static void o2nm_node_group_drop_item(struct config_group *group, struct config_item *item) { struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster = to_o2nm_cluster(group->cg_item.ci_parent); if (cluster->cl_nodes[node->nd_num] == node) { o2net_disconnect_node(node); if (cluster->cl_has_local && (cluster->cl_local_node == node->nd_num)) { cluster->cl_has_local = 0; cluster->cl_local_node = O2NM_INVALID_NODE_NUM; o2net_stop_listening(node); } } /* XXX call into net to stop this node from trading messages */ write_lock(&cluster->cl_nodes_lock); /* XXX sloppy */ if (node->nd_ipv4_address) rb_erase(&node->nd_ip_node, &cluster->cl_node_ip_tree); /* nd_num might be 0 if the node number hasn't been set.. */ if (cluster->cl_nodes[node->nd_num] == node) { cluster->cl_nodes[node->nd_num] = NULL; clear_bit(node->nd_num, cluster->cl_nodes_bitmap); } write_unlock(&cluster->cl_nodes_lock); mlog(ML_CLUSTER, "o2nm: Unregistered node %s\n", config_item_name(&node->nd_item)); config_item_put(item); } static struct configfs_group_operations o2nm_node_group_group_ops = { .make_item = o2nm_node_group_make_item, .drop_item = o2nm_node_group_drop_item, }; static const struct config_item_type o2nm_node_group_type = { .ct_group_ops = &o2nm_node_group_group_ops, .ct_owner = THIS_MODULE, }; /* cluster */ static void o2nm_cluster_release(struct config_item *item) { struct o2nm_cluster *cluster = to_o2nm_cluster(item); kfree(cluster); } static struct configfs_item_operations o2nm_cluster_item_ops = { .release = o2nm_cluster_release, }; static const struct config_item_type o2nm_cluster_type = { .ct_item_ops = &o2nm_cluster_item_ops, .ct_attrs = o2nm_cluster_attrs, .ct_owner = THIS_MODULE, }; /* cluster set */ struct o2nm_cluster_group { struct configfs_subsystem cs_subsys; /* some stuff? */ }; #if 0 static struct o2nm_cluster_group *to_o2nm_cluster_group(struct config_group *group) { return group ? container_of(to_configfs_subsystem(group), struct o2nm_cluster_group, cs_subsys) : NULL; } #endif static struct config_group *o2nm_cluster_group_make_group(struct config_group *group, const char *name) { struct o2nm_cluster *cluster = NULL; struct o2nm_node_group *ns = NULL; struct config_group *o2hb_group = NULL, *ret = NULL; /* this runs under the parent dir's i_rwsem; there can be only * one caller in here at a time */ if (o2nm_single_cluster) return ERR_PTR(-ENOSPC); cluster = kzalloc(sizeof(struct o2nm_cluster), GFP_KERNEL); ns = kzalloc(sizeof(struct o2nm_node_group), GFP_KERNEL); o2hb_group = o2hb_alloc_hb_set(); if (cluster == NULL || ns == NULL || o2hb_group == NULL) goto out; config_group_init_type_name(&cluster->cl_group, name, &o2nm_cluster_type); configfs_add_default_group(&ns->ns_group, &cluster->cl_group); config_group_init_type_name(&ns->ns_group, "node", &o2nm_node_group_type); configfs_add_default_group(o2hb_group, &cluster->cl_group); rwlock_init(&cluster->cl_nodes_lock); cluster->cl_node_ip_tree = RB_ROOT; cluster->cl_reconnect_delay_ms = O2NET_RECONNECT_DELAY_MS_DEFAULT; cluster->cl_idle_timeout_ms = O2NET_IDLE_TIMEOUT_MS_DEFAULT; cluster->cl_keepalive_delay_ms = O2NET_KEEPALIVE_DELAY_MS_DEFAULT; cluster->cl_fence_method = O2NM_FENCE_RESET; ret = &cluster->cl_group; o2nm_single_cluster = cluster; out: if (ret == NULL) { kfree(cluster); kfree(ns); o2hb_free_hb_set(o2hb_group); ret = ERR_PTR(-ENOMEM); } return ret; } static void o2nm_cluster_group_drop_item(struct config_group *group, struct config_item *item) { struct o2nm_cluster *cluster = to_o2nm_cluster(item); BUG_ON(o2nm_single_cluster != cluster); o2nm_single_cluster = NULL; configfs_remove_default_groups(&cluster->cl_group); config_item_put(item); } static struct configfs_group_operations o2nm_cluster_group_group_ops = { .make_group = o2nm_cluster_group_make_group, .drop_item = o2nm_cluster_group_drop_item, }; static const struct config_item_type o2nm_cluster_group_type = { .ct_group_ops = &o2nm_cluster_group_group_ops, .ct_owner = THIS_MODULE, }; static struct o2nm_cluster_group o2nm_cluster_group = { .cs_subsys = { .su_group = { .cg_item = { .ci_namebuf = "cluster", .ci_type = &o2nm_cluster_group_type, }, }, }, }; static inline void o2nm_lock_subsystem(void) { mutex_lock(&o2nm_cluster_group.cs_subsys.su_mutex); } static inline void o2nm_unlock_subsystem(void) { mutex_unlock(&o2nm_cluster_group.cs_subsys.su_mutex); } int o2nm_depend_item(struct config_item *item) { return configfs_depend_item(&o2nm_cluster_group.cs_subsys, item); } void o2nm_undepend_item(struct config_item *item) { configfs_undepend_item(item); } int o2nm_depend_this_node(void) { int ret = 0; struct o2nm_node *local_node; local_node = o2nm_get_node_by_num(o2nm_this_node()); if (!local_node) { ret = -EINVAL; goto out; } ret = o2nm_depend_item(&local_node->nd_item); o2nm_node_put(local_node); out: return ret; } void o2nm_undepend_this_node(void) { struct o2nm_node *local_node; local_node = o2nm_get_node_by_num(o2nm_this_node()); BUG_ON(!local_node); o2nm_undepend_item(&local_node->nd_item); o2nm_node_put(local_node); } static void __exit exit_o2nm(void) { /* XXX sync with hb callbacks and shut down hb? */ o2net_unregister_hb_callbacks(); configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys); o2cb_sys_shutdown(); o2net_exit(); o2hb_exit(); } static int __init init_o2nm(void) { int ret; o2hb_init(); ret = o2net_init(); if (ret) goto out_o2hb; ret = o2net_register_hb_callbacks(); if (ret) goto out_o2net; config_group_init(&o2nm_cluster_group.cs_subsys.su_group); mutex_init(&o2nm_cluster_group.cs_subsys.su_mutex); ret = configfs_register_subsystem(&o2nm_cluster_group.cs_subsys); if (ret) { printk(KERN_ERR "nodemanager: Registration returned %d\n", ret); goto out_callbacks; } ret = o2cb_sys_init(); if (!ret) goto out; configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys); out_callbacks: o2net_unregister_hb_callbacks(); out_o2net: o2net_exit(); out_o2hb: o2hb_exit(); out: return ret; } MODULE_AUTHOR("Oracle"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("OCFS2 cluster management"); module_init(init_o2nm) module_exit(exit_o2nm) |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 | // SPDX-License-Identifier: GPL-2.0-only /* * Fd transport layer. Includes deprecated socket layer. * * Copyright (C) 2006 by Russ Cox <rsc@swtch.com> * Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net> * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/module.h> #include <linux/net.h> #include <linux/ipv6.h> #include <linux/kthread.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/un.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/file.h> #include <linux/parser.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include <linux/syscalls.h> /* killme */ #define P9_PORT 564 #define MAX_SOCK_BUF (1024*1024) #define MAXPOLLWADDR 2 static struct p9_trans_module p9_tcp_trans; static struct p9_trans_module p9_fd_trans; /** * struct p9_fd_opts - per-transport options * @rfd: file descriptor for reading (trans=fd) * @wfd: file descriptor for writing (trans=fd) * @port: port to connect to (trans=tcp) * @privport: port is privileged */ struct p9_fd_opts { int rfd; int wfd; u16 port; bool privport; }; /* * Option Parsing (code inspired by NFS code) * - a little lazy - parse all fd-transport options */ enum { /* Options that take integer arguments */ Opt_port, Opt_rfdno, Opt_wfdno, Opt_err, /* Options that take no arguments */ Opt_privport, }; static const match_table_t tokens = { {Opt_port, "port=%u"}, {Opt_rfdno, "rfdno=%u"}, {Opt_wfdno, "wfdno=%u"}, {Opt_privport, "privport"}, {Opt_err, NULL}, }; enum { Rworksched = 1, /* read work scheduled or running */ Rpending = 2, /* can read */ Wworksched = 4, /* write work scheduled or running */ Wpending = 8, /* can write */ }; struct p9_poll_wait { struct p9_conn *conn; wait_queue_entry_t wait; wait_queue_head_t *wait_addr; }; /** * struct p9_conn - fd mux connection state information * @mux_list: list link for mux to manage multiple connections (?) * @client: reference to client instance for this connection * @err: error state * @req_lock: lock protecting req_list and requests statuses * @req_list: accounting for requests which have been sent * @unsent_req_list: accounting for requests that haven't been sent * @rreq: read request * @wreq: write request * @tmp_buf: temporary buffer to read in header * @rc: temporary fcall for reading current frame * @wpos: write position for current frame * @wsize: amount of data to write for current frame * @wbuf: current write buffer * @poll_pending_link: pending links to be polled per conn * @poll_wait: array of wait_q's for various worker threads * @pt: poll state * @rq: current read work * @wq: current write work * @wsched: ???? * */ struct p9_conn { struct list_head mux_list; struct p9_client *client; int err; spinlock_t req_lock; struct list_head req_list; struct list_head unsent_req_list; struct p9_req_t *rreq; struct p9_req_t *wreq; char tmp_buf[P9_HDRSZ]; struct p9_fcall rc; int wpos; int wsize; char *wbuf; struct list_head poll_pending_link; struct p9_poll_wait poll_wait[MAXPOLLWADDR]; poll_table pt; struct work_struct rq; struct work_struct wq; unsigned long wsched; }; /** * struct p9_trans_fd - transport state * @rd: reference to file to read from * @wr: reference of file to write to * @conn: connection state reference * */ struct p9_trans_fd { struct file *rd; struct file *wr; struct p9_conn conn; }; static void p9_poll_workfn(struct work_struct *work); static DEFINE_SPINLOCK(p9_poll_lock); static LIST_HEAD(p9_poll_pending_list); static DECLARE_WORK(p9_poll_work, p9_poll_workfn); static unsigned int p9_ipport_resv_min = P9_DEF_MIN_RESVPORT; static unsigned int p9_ipport_resv_max = P9_DEF_MAX_RESVPORT; static void p9_mux_poll_stop(struct p9_conn *m) { unsigned long flags; int i; for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) { struct p9_poll_wait *pwait = &m->poll_wait[i]; if (pwait->wait_addr) { remove_wait_queue(pwait->wait_addr, &pwait->wait); pwait->wait_addr = NULL; } } spin_lock_irqsave(&p9_poll_lock, flags); list_del_init(&m->poll_pending_link); spin_unlock_irqrestore(&p9_poll_lock, flags); flush_work(&p9_poll_work); } /** * p9_conn_cancel - cancel all pending requests with error * @m: mux data * @err: error code * */ static void p9_conn_cancel(struct p9_conn *m, int err) { struct p9_req_t *req, *rtmp; LIST_HEAD(cancel_list); p9_debug(P9_DEBUG_ERROR, "mux %p err %d\n", m, err); spin_lock(&m->req_lock); if (m->err) { spin_unlock(&m->req_lock); return; } m->err = err; list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) { list_move(&req->req_list, &cancel_list); WRITE_ONCE(req->status, REQ_STATUS_ERROR); } list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) { list_move(&req->req_list, &cancel_list); WRITE_ONCE(req->status, REQ_STATUS_ERROR); } spin_unlock(&m->req_lock); list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) { p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req); list_del(&req->req_list); if (!req->t_err) req->t_err = err; p9_client_cb(m->client, req, REQ_STATUS_ERROR); } } static __poll_t p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err) { __poll_t ret; struct p9_trans_fd *ts = NULL; if (client && client->status == Connected) ts = client->trans; if (!ts) { if (err) *err = -EREMOTEIO; return EPOLLERR; } ret = vfs_poll(ts->rd, pt); if (ts->rd != ts->wr) ret = (ret & ~EPOLLOUT) | (vfs_poll(ts->wr, pt) & ~EPOLLIN); return ret; } /** * p9_fd_read- read from a fd * @client: client instance * @v: buffer to receive data into * @len: size of receive buffer * */ static int p9_fd_read(struct p9_client *client, void *v, int len) { int ret; struct p9_trans_fd *ts = NULL; loff_t pos; if (client && client->status != Disconnected) ts = client->trans; if (!ts) return -EREMOTEIO; if (!(ts->rd->f_flags & O_NONBLOCK)) p9_debug(P9_DEBUG_ERROR, "blocking read ...\n"); pos = ts->rd->f_pos; ret = kernel_read(ts->rd, v, len, &pos); if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN) client->status = Disconnected; return ret; } /** * p9_read_work - called when there is some data to be read from a transport * @work: container of work to be done * */ static void p9_read_work(struct work_struct *work) { __poll_t n; int err; struct p9_conn *m; m = container_of(work, struct p9_conn, rq); if (m->err < 0) return; p9_debug(P9_DEBUG_TRANS, "start mux %p pos %zd\n", m, m->rc.offset); if (!m->rc.sdata) { m->rc.sdata = m->tmp_buf; m->rc.offset = 0; m->rc.capacity = P9_HDRSZ; /* start by reading header */ } clear_bit(Rpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "read mux %p pos %zd size: %zd = %zd\n", m, m->rc.offset, m->rc.capacity, m->rc.capacity - m->rc.offset); err = p9_fd_read(m->client, m->rc.sdata + m->rc.offset, m->rc.capacity - m->rc.offset); p9_debug(P9_DEBUG_TRANS, "mux %p got %d bytes\n", m, err); if (err == -EAGAIN) goto end_clear; if (err <= 0) goto error; m->rc.offset += err; /* header read in */ if ((!m->rreq) && (m->rc.offset == m->rc.capacity)) { p9_debug(P9_DEBUG_TRANS, "got new header\n"); /* Header size */ m->rc.size = P9_HDRSZ; err = p9_parse_header(&m->rc, &m->rc.size, NULL, NULL, 0); if (err) { p9_debug(P9_DEBUG_ERROR, "error parsing header: %d\n", err); goto error; } p9_debug(P9_DEBUG_TRANS, "mux %p pkt: size: %d bytes tag: %d\n", m, m->rc.size, m->rc.tag); m->rreq = p9_tag_lookup(m->client, m->rc.tag); if (!m->rreq || (m->rreq->status != REQ_STATUS_SENT)) { p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n", m->rc.tag); err = -EIO; goto error; } if (m->rc.size > m->rreq->rc.capacity) { p9_debug(P9_DEBUG_ERROR, "requested packet size too big: %d for tag %d with capacity %zd\n", m->rc.size, m->rc.tag, m->rreq->rc.capacity); err = -EIO; goto error; } if (!m->rreq->rc.sdata) { p9_debug(P9_DEBUG_ERROR, "No recv fcall for tag %d (req %p), disconnecting!\n", m->rc.tag, m->rreq); p9_req_put(m->client, m->rreq); m->rreq = NULL; err = -EIO; goto error; } m->rc.sdata = m->rreq->rc.sdata; memcpy(m->rc.sdata, m->tmp_buf, m->rc.capacity); m->rc.capacity = m->rc.size; } /* packet is read in * not an else because some packets (like clunk) have no payload */ if ((m->rreq) && (m->rc.offset == m->rc.capacity)) { p9_debug(P9_DEBUG_TRANS, "got new packet\n"); m->rreq->rc.size = m->rc.offset; spin_lock(&m->req_lock); if (m->rreq->status == REQ_STATUS_SENT) { list_del(&m->rreq->req_list); p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD); } else if (m->rreq->status == REQ_STATUS_FLSHD) { /* Ignore replies associated with a cancelled request. */ p9_debug(P9_DEBUG_TRANS, "Ignore replies associated with a cancelled request\n"); } else { spin_unlock(&m->req_lock); p9_debug(P9_DEBUG_ERROR, "Request tag %d errored out while we were reading the reply\n", m->rc.tag); err = -EIO; goto error; } spin_unlock(&m->req_lock); m->rc.sdata = NULL; m->rc.offset = 0; m->rc.capacity = 0; p9_req_put(m->client, m->rreq); m->rreq = NULL; } end_clear: clear_bit(Rworksched, &m->wsched); if (!list_empty(&m->req_list)) { if (test_and_clear_bit(Rpending, &m->wsched)) n = EPOLLIN; else n = p9_fd_poll(m->client, NULL, NULL); if ((n & EPOLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m); schedule_work(&m->rq); } } return; error: p9_conn_cancel(m, err); clear_bit(Rworksched, &m->wsched); } /** * p9_fd_write - write to a socket * @client: client instance * @v: buffer to send data from * @len: size of send buffer * */ static int p9_fd_write(struct p9_client *client, void *v, int len) { ssize_t ret; struct p9_trans_fd *ts = NULL; if (client && client->status != Disconnected) ts = client->trans; if (!ts) return -EREMOTEIO; if (!(ts->wr->f_flags & O_NONBLOCK)) p9_debug(P9_DEBUG_ERROR, "blocking write ...\n"); ret = kernel_write(ts->wr, v, len, &ts->wr->f_pos); if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN) client->status = Disconnected; return ret; } /** * p9_write_work - called when a transport can send some data * @work: container for work to be done * */ static void p9_write_work(struct work_struct *work) { __poll_t n; int err; struct p9_conn *m; struct p9_req_t *req; m = container_of(work, struct p9_conn, wq); if (m->err < 0) { clear_bit(Wworksched, &m->wsched); return; } if (!m->wsize) { spin_lock(&m->req_lock); if (list_empty(&m->unsent_req_list)) { clear_bit(Wworksched, &m->wsched); spin_unlock(&m->req_lock); return; } req = list_entry(m->unsent_req_list.next, struct p9_req_t, req_list); WRITE_ONCE(req->status, REQ_STATUS_SENT); p9_debug(P9_DEBUG_TRANS, "move req %p\n", req); list_move_tail(&req->req_list, &m->req_list); m->wbuf = req->tc.sdata; m->wsize = req->tc.size; m->wpos = 0; p9_req_get(req); m->wreq = req; spin_unlock(&m->req_lock); } p9_debug(P9_DEBUG_TRANS, "mux %p pos %d size %d\n", m, m->wpos, m->wsize); clear_bit(Wpending, &m->wsched); err = p9_fd_write(m->client, m->wbuf + m->wpos, m->wsize - m->wpos); p9_debug(P9_DEBUG_TRANS, "mux %p sent %d bytes\n", m, err); if (err == -EAGAIN) goto end_clear; if (err < 0) goto error; else if (err == 0) { err = -EREMOTEIO; goto error; } m->wpos += err; if (m->wpos == m->wsize) { m->wpos = m->wsize = 0; p9_req_put(m->client, m->wreq); m->wreq = NULL; } end_clear: clear_bit(Wworksched, &m->wsched); if (m->wsize || !list_empty(&m->unsent_req_list)) { if (test_and_clear_bit(Wpending, &m->wsched)) n = EPOLLOUT; else n = p9_fd_poll(m->client, NULL, NULL); if ((n & EPOLLOUT) && !test_and_set_bit(Wworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m); schedule_work(&m->wq); } } return; error: p9_conn_cancel(m, err); clear_bit(Wworksched, &m->wsched); } static int p9_pollwake(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { struct p9_poll_wait *pwait = container_of(wait, struct p9_poll_wait, wait); struct p9_conn *m = pwait->conn; unsigned long flags; spin_lock_irqsave(&p9_poll_lock, flags); if (list_empty(&m->poll_pending_link)) list_add_tail(&m->poll_pending_link, &p9_poll_pending_list); spin_unlock_irqrestore(&p9_poll_lock, flags); schedule_work(&p9_poll_work); return 1; } /** * p9_pollwait - add poll task to the wait queue * @filp: file pointer being polled * @wait_address: wait_q to block on * @p: poll state * * called by files poll operation to add v9fs-poll task to files wait queue */ static void p9_pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { struct p9_conn *m = container_of(p, struct p9_conn, pt); struct p9_poll_wait *pwait = NULL; int i; for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) { if (m->poll_wait[i].wait_addr == NULL) { pwait = &m->poll_wait[i]; break; } } if (!pwait) { p9_debug(P9_DEBUG_ERROR, "not enough wait_address slots\n"); return; } pwait->conn = m; pwait->wait_addr = wait_address; init_waitqueue_func_entry(&pwait->wait, p9_pollwake); add_wait_queue(wait_address, &pwait->wait); } /** * p9_conn_create - initialize the per-session mux data * @client: client instance * * Note: Creates the polling task if this is the first session. */ static void p9_conn_create(struct p9_client *client) { __poll_t n; struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "client %p msize %d\n", client, client->msize); INIT_LIST_HEAD(&m->mux_list); m->client = client; spin_lock_init(&m->req_lock); INIT_LIST_HEAD(&m->req_list); INIT_LIST_HEAD(&m->unsent_req_list); INIT_WORK(&m->rq, p9_read_work); INIT_WORK(&m->wq, p9_write_work); INIT_LIST_HEAD(&m->poll_pending_link); init_poll_funcptr(&m->pt, p9_pollwait); n = p9_fd_poll(client, &m->pt, NULL); if (n & EPOLLIN) { p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m); set_bit(Rpending, &m->wsched); } if (n & EPOLLOUT) { p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); set_bit(Wpending, &m->wsched); } } /** * p9_poll_mux - polls a mux and schedules read or write works if necessary * @m: connection to poll * */ static void p9_poll_mux(struct p9_conn *m) { __poll_t n; int err = -ECONNRESET; if (m->err < 0) return; n = p9_fd_poll(m->client, NULL, &err); if (n & (EPOLLERR | EPOLLHUP | EPOLLNVAL)) { p9_debug(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n); p9_conn_cancel(m, err); } if (n & EPOLLIN) { set_bit(Rpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m); if (!test_and_set_bit(Rworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m); schedule_work(&m->rq); } } if (n & EPOLLOUT) { set_bit(Wpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); if ((m->wsize || !list_empty(&m->unsent_req_list)) && !test_and_set_bit(Wworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m); schedule_work(&m->wq); } } } /** * p9_fd_request - send 9P request * The function can sleep until the request is scheduled for sending. * The function can be interrupted. Return from the function is not * a guarantee that the request is sent successfully. * * @client: client instance * @req: request to be sent * */ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req) { __poll_t n; struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n", m, current, &req->tc, req->tc.id); spin_lock(&m->req_lock); if (m->err < 0) { spin_unlock(&m->req_lock); return m->err; } WRITE_ONCE(req->status, REQ_STATUS_UNSENT); list_add_tail(&req->req_list, &m->unsent_req_list); spin_unlock(&m->req_lock); if (test_and_clear_bit(Wpending, &m->wsched)) n = EPOLLOUT; else n = p9_fd_poll(m->client, NULL, NULL); if (n & EPOLLOUT && !test_and_set_bit(Wworksched, &m->wsched)) schedule_work(&m->wq); return 0; } static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req) { struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; int ret = 1; p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); spin_lock(&m->req_lock); if (req->status == REQ_STATUS_UNSENT) { list_del(&req->req_list); WRITE_ONCE(req->status, REQ_STATUS_FLSHD); p9_req_put(client, req); ret = 0; } spin_unlock(&m->req_lock); return ret; } static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) { struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); spin_lock(&m->req_lock); /* Ignore cancelled request if message has been received * before lock. */ if (req->status == REQ_STATUS_RCVD) { spin_unlock(&m->req_lock); return 0; } /* we haven't received a response for oldreq, * remove it from the list. */ list_del(&req->req_list); WRITE_ONCE(req->status, REQ_STATUS_FLSHD); spin_unlock(&m->req_lock); p9_req_put(client, req); return 0; } static int p9_fd_show_options(struct seq_file *m, struct p9_client *clnt) { if (clnt->trans_mod == &p9_tcp_trans) { if (clnt->trans_opts.tcp.port != P9_PORT) seq_printf(m, ",port=%u", clnt->trans_opts.tcp.port); } else if (clnt->trans_mod == &p9_fd_trans) { if (clnt->trans_opts.fd.rfd != ~0) seq_printf(m, ",rfd=%u", clnt->trans_opts.fd.rfd); if (clnt->trans_opts.fd.wfd != ~0) seq_printf(m, ",wfd=%u", clnt->trans_opts.fd.wfd); } return 0; } /** * parse_opts - parse mount options into p9_fd_opts structure * @params: options string passed from mount * @opts: fd transport-specific structure to parse options into * * Returns 0 upon success, -ERRNO upon failure */ static int parse_opts(char *params, struct p9_fd_opts *opts) { char *p; substring_t args[MAX_OPT_ARGS]; int option; char *options, *tmp_options; opts->port = P9_PORT; opts->rfd = ~0; opts->wfd = ~0; opts->privport = false; if (!params) return 0; tmp_options = kstrdup(params, GFP_KERNEL); if (!tmp_options) { p9_debug(P9_DEBUG_ERROR, "failed to allocate copy of option string\n"); return -ENOMEM; } options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token; int r; if (!*p) continue; token = match_token(p, tokens, args); if ((token != Opt_err) && (token != Opt_privport)) { r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); continue; } } switch (token) { case Opt_port: opts->port = option; break; case Opt_rfdno: opts->rfd = option; break; case Opt_wfdno: opts->wfd = option; break; case Opt_privport: opts->privport = true; break; default: continue; } } kfree(tmp_options); return 0; } static int p9_fd_open(struct p9_client *client, int rfd, int wfd) { struct p9_trans_fd *ts = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); if (!ts) return -ENOMEM; ts->rd = fget(rfd); if (!ts->rd) goto out_free_ts; if (!(ts->rd->f_mode & FMODE_READ)) goto out_put_rd; /* Prevent workers from hanging on IO when fd is a pipe. * It's technically possible for userspace or concurrent mounts to * modify this flag concurrently, which will likely result in a * broken filesystem. However, just having bad flags here should * not crash the kernel or cause any other sort of bug, so mark this * particular data race as intentional so that tooling (like KCSAN) * can allow it and detect further problems. */ data_race(ts->rd->f_flags |= O_NONBLOCK); ts->wr = fget(wfd); if (!ts->wr) goto out_put_rd; if (!(ts->wr->f_mode & FMODE_WRITE)) goto out_put_wr; data_race(ts->wr->f_flags |= O_NONBLOCK); client->trans = ts; client->status = Connected; return 0; out_put_wr: fput(ts->wr); out_put_rd: fput(ts->rd); out_free_ts: kfree(ts); return -EIO; } static int p9_socket_open(struct p9_client *client, struct socket *csocket) { struct p9_trans_fd *p; struct file *file; p = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); if (!p) { sock_release(csocket); return -ENOMEM; } csocket->sk->sk_allocation = GFP_NOIO; csocket->sk->sk_use_task_frag = false; file = sock_alloc_file(csocket, 0, NULL); if (IS_ERR(file)) { pr_err("%s (%d): failed to map fd\n", __func__, task_pid_nr(current)); kfree(p); return PTR_ERR(file); } get_file(file); p->wr = p->rd = file; client->trans = p; client->status = Connected; p->rd->f_flags |= O_NONBLOCK; p9_conn_create(client); return 0; } /** * p9_conn_destroy - cancels all pending requests of mux * @m: mux to destroy * */ static void p9_conn_destroy(struct p9_conn *m) { p9_debug(P9_DEBUG_TRANS, "mux %p prev %p next %p\n", m, m->mux_list.prev, m->mux_list.next); p9_mux_poll_stop(m); cancel_work_sync(&m->rq); if (m->rreq) { p9_req_put(m->client, m->rreq); m->rreq = NULL; } cancel_work_sync(&m->wq); if (m->wreq) { p9_req_put(m->client, m->wreq); m->wreq = NULL; } p9_conn_cancel(m, -ECONNRESET); m->client = NULL; } /** * p9_fd_close - shutdown file descriptor transport * @client: client instance * */ static void p9_fd_close(struct p9_client *client) { struct p9_trans_fd *ts; if (!client) return; ts = client->trans; if (!ts) return; client->status = Disconnected; p9_conn_destroy(&ts->conn); if (ts->rd) fput(ts->rd); if (ts->wr) fput(ts->wr); kfree(ts); } /* * stolen from NFS - maybe should be made a generic function? */ static inline int valid_ipaddr4(const char *buf) { int rc, count, in[4]; rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]); if (rc != 4) return -EINVAL; for (count = 0; count < 4; count++) { if (in[count] > 255) return -EINVAL; } return 0; } static int p9_bind_privport(struct socket *sock) { struct sockaddr_in cl; int port, err = -EINVAL; memset(&cl, 0, sizeof(cl)); cl.sin_family = AF_INET; cl.sin_addr.s_addr = htonl(INADDR_ANY); for (port = p9_ipport_resv_max; port >= p9_ipport_resv_min; port--) { cl.sin_port = htons((ushort)port); err = kernel_bind(sock, (struct sockaddr *)&cl, sizeof(cl)); if (err != -EADDRINUSE) break; } return err; } static int p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) { int err; struct socket *csocket; struct sockaddr_in sin_server; struct p9_fd_opts opts; err = parse_opts(args, &opts); if (err < 0) return err; if (addr == NULL || valid_ipaddr4(addr) < 0) return -EINVAL; csocket = NULL; client->trans_opts.tcp.port = opts.port; client->trans_opts.tcp.privport = opts.privport; sin_server.sin_family = AF_INET; sin_server.sin_addr.s_addr = in_aton(addr); sin_server.sin_port = htons(opts.port); err = __sock_create(current->nsproxy->net_ns, PF_INET, SOCK_STREAM, IPPROTO_TCP, &csocket, 1); if (err) { pr_err("%s (%d): problem creating socket\n", __func__, task_pid_nr(current)); return err; } if (opts.privport) { err = p9_bind_privport(csocket); if (err < 0) { pr_err("%s (%d): problem binding to privport\n", __func__, task_pid_nr(current)); sock_release(csocket); return err; } } err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr *)&sin_server, sizeof(struct sockaddr_in), 0); if (err < 0) { pr_err("%s (%d): problem connecting socket to %s\n", __func__, task_pid_nr(current), addr); sock_release(csocket); return err; } return p9_socket_open(client, csocket); } static int p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) { int err; struct socket *csocket; struct sockaddr_un sun_server; csocket = NULL; if (!addr || !strlen(addr)) return -EINVAL; if (strlen(addr) >= UNIX_PATH_MAX) { pr_err("%s (%d): address too long: %s\n", __func__, task_pid_nr(current), addr); return -ENAMETOOLONG; } sun_server.sun_family = PF_UNIX; strcpy(sun_server.sun_path, addr); err = __sock_create(current->nsproxy->net_ns, PF_UNIX, SOCK_STREAM, 0, &csocket, 1); if (err < 0) { pr_err("%s (%d): problem creating socket\n", __func__, task_pid_nr(current)); return err; } err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr *)&sun_server, sizeof(struct sockaddr_un) - 1, 0); if (err < 0) { pr_err("%s (%d): problem connecting socket: %s: %d\n", __func__, task_pid_nr(current), addr, err); sock_release(csocket); return err; } return p9_socket_open(client, csocket); } static int p9_fd_create(struct p9_client *client, const char *addr, char *args) { int err; struct p9_fd_opts opts; err = parse_opts(args, &opts); if (err < 0) return err; client->trans_opts.fd.rfd = opts.rfd; client->trans_opts.fd.wfd = opts.wfd; if (opts.rfd == ~0 || opts.wfd == ~0) { pr_err("Insufficient options for proto=fd\n"); return -ENOPROTOOPT; } err = p9_fd_open(client, opts.rfd, opts.wfd); if (err < 0) return err; p9_conn_create(client); return 0; } static struct p9_trans_module p9_tcp_trans = { .name = "tcp", .maxsize = MAX_SOCK_BUF, .pooled_rbuffers = false, .def = 0, .create = p9_fd_create_tcp, .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; MODULE_ALIAS_9P("tcp"); static struct p9_trans_module p9_unix_trans = { .name = "unix", .maxsize = MAX_SOCK_BUF, .def = 0, .create = p9_fd_create_unix, .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; MODULE_ALIAS_9P("unix"); static struct p9_trans_module p9_fd_trans = { .name = "fd", .maxsize = MAX_SOCK_BUF, .def = 0, .create = p9_fd_create, .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; MODULE_ALIAS_9P("fd"); /** * p9_poll_workfn - poll worker thread * @work: work queue * * polls all v9fs transports for new events and queues the appropriate * work to the work queue * */ static void p9_poll_workfn(struct work_struct *work) { unsigned long flags; p9_debug(P9_DEBUG_TRANS, "start %p\n", current); spin_lock_irqsave(&p9_poll_lock, flags); while (!list_empty(&p9_poll_pending_list)) { struct p9_conn *conn = list_first_entry(&p9_poll_pending_list, struct p9_conn, poll_pending_link); list_del_init(&conn->poll_pending_link); spin_unlock_irqrestore(&p9_poll_lock, flags); p9_poll_mux(conn); spin_lock_irqsave(&p9_poll_lock, flags); } spin_unlock_irqrestore(&p9_poll_lock, flags); p9_debug(P9_DEBUG_TRANS, "finish\n"); } static int __init p9_trans_fd_init(void) { v9fs_register_trans(&p9_tcp_trans); v9fs_register_trans(&p9_unix_trans); v9fs_register_trans(&p9_fd_trans); return 0; } static void __exit p9_trans_fd_exit(void) { flush_work(&p9_poll_work); v9fs_unregister_trans(&p9_tcp_trans); v9fs_unregister_trans(&p9_unix_trans); v9fs_unregister_trans(&p9_fd_trans); } module_init(p9_trans_fd_init); module_exit(p9_trans_fd_exit); MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>"); MODULE_DESCRIPTION("Filedescriptor Transport for 9P"); MODULE_LICENSE("GPL"); |
| 2 2 1 1 1 1 873 872 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/zswap.h> #include <linux/plist.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include "internal.h" #include "swap.h" static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); static struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full*/ #define TTRS_FULL 0x4 /* * returns number of pages in the folio that backs the swap entry. If positive, * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no * folio was associated with the swap entry. */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct folio *folio; int ret = 0; folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry)); if (IS_ERR(folio)) return 0; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming folios. So we hold a folio lock * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ if (folio_trylock(folio)) { if ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))) ret = folio_free_swap(folio); folio_unlock(folio); } ret = ret ? folio_nr_pages(folio) : -folio_nr_pages(folio); folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_folio_sector(struct folio *folio) { struct swap_info_struct *sis = swp_swap_info(folio->swap); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = swp_offset(folio->swap); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_order(order) (order) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_order() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_order(order) 0 #endif #define LATENCY_LIMIT 256 static inline void cluster_set_flag(struct swap_cluster_info *info, unsigned int flag) { info->flags = flag; } static inline unsigned int cluster_count(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_count(struct swap_cluster_info *info, unsigned int c) { info->data = c; } static inline void cluster_set_count_flag(struct swap_cluster_info *info, unsigned int c, unsigned int f) { info->flags = f; info->data = c; } static inline unsigned int cluster_next(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_next(struct swap_cluster_info *info, unsigned int n) { info->data = n; } static inline void cluster_set_next_flag(struct swap_cluster_info *info, unsigned int n, unsigned int f) { info->flags = f; info->data = n; } static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; } static inline bool cluster_is_null(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_NEXT_NULL; } static inline void cluster_set_null(struct swap_cluster_info *info) { info->flags = CLUSTER_FLAG_NEXT_NULL; info->data = 0; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = si->cluster_info; if (ci) { ci += offset / SWAPFILE_CLUSTER; spin_lock(&ci->lock); } return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { if (ci) spin_unlock(&ci->lock); } /* * Determine the locking method in use for this device. Return * swap_cluster_info if SSD-style cluster-based locking is in place. */ static inline struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; /* Try to use fine-grained SSD-style locking if available: */ ci = lock_cluster(si, offset); /* Otherwise, fall back to traditional, coarse locking: */ if (!ci) spin_lock(&si->lock); return ci; } static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci) { if (ci) unlock_cluster(ci); else spin_unlock(&si->lock); } static inline bool cluster_list_empty(struct swap_cluster_list *list) { return cluster_is_null(&list->head); } static inline unsigned int cluster_list_first(struct swap_cluster_list *list) { return cluster_next(&list->head); } static void cluster_list_init(struct swap_cluster_list *list) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } static void cluster_list_add_tail(struct swap_cluster_list *list, struct swap_cluster_info *ci, unsigned int idx) { if (cluster_list_empty(list)) { cluster_set_next_flag(&list->head, idx, 0); cluster_set_next_flag(&list->tail, idx, 0); } else { struct swap_cluster_info *ci_tail; unsigned int tail = cluster_next(&list->tail); /* * Nested cluster lock, but both cluster locks are * only acquired when we held swap_info_struct->lock */ ci_tail = ci + tail; spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); cluster_set_next(ci_tail, idx); spin_unlock(&ci_tail->lock); cluster_set_next_flag(&list->tail, idx, 0); } } static unsigned int cluster_list_del_first(struct swap_cluster_list *list, struct swap_cluster_info *ci) { unsigned int idx; idx = cluster_next(&list->head); if (cluster_next(&list->tail) == idx) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } else cluster_set_next_flag(&list->head, cluster_next(&ci[idx]), 0); return idx; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) { /* * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE); cluster_list_add_tail(&si->free_clusters, ci, idx); } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. caller should hold si->lock. */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *info, *ci; unsigned int idx; info = si->cluster_info; while (!cluster_list_empty(&si->discard_clusters)) { idx = cluster_list_del_first(&si->discard_clusters, info); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); __free_cluster(si, idx); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); unlock_cluster(ci); } } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); spin_lock(&si->lock); swap_do_scheduled_discard(si); spin_unlock(&si->lock); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx); cluster_list_del_first(&si->free_clusters, ci); cluster_set_count_flag(ci + idx, 0, 0); } static void free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info + idx; VM_BUG_ON(cluster_count(ci) != 0); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, idx); return; } __free_cluster(si, idx); } /* * The cluster corresponding to page_nr will be used. The cluster will be * removed from free cluster list and its usage counter will be increased by * count. */ static void add_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr, unsigned long count) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; if (cluster_is_free(&cluster_info[idx])) alloc_cluster(p, idx); VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) + count); } /* * The cluster corresponding to page_nr will be used. The cluster will be * removed from free cluster list and its usage counter will be increased by 1. */ static void inc_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { add_cluster_info_page(p, cluster_info, page_nr, 1); } /* * The cluster corresponding to page_nr decreases one usage. If the usage * counter becomes 0, which means no page in the cluster is in using, we can * optionally discard the cluster and add it to free cluster list. */ static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) - 1); if (cluster_count(&cluster_info[idx]) == 0) free_cluster(p, idx); } /* * It's possible scan_swap_map_slots() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */ static bool scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, unsigned long offset, int order) { struct percpu_cluster *percpu_cluster; bool conflict; offset /= SWAPFILE_CLUSTER; conflict = !cluster_list_empty(&si->free_clusters) && offset != cluster_list_first(&si->free_clusters) && cluster_is_free(&si->cluster_info[offset]); if (!conflict) return false; percpu_cluster = this_cpu_ptr(si->percpu_cluster); percpu_cluster->next[order] = SWAP_NEXT_INVALID; return true; } static inline bool swap_range_empty(char *swap_map, unsigned int start, unsigned int nr_pages) { unsigned int i; for (i = 0; i < nr_pages; i++) { if (swap_map[start + i]) return false; } return true; } /* * Try to get swap entries with specified order from current cpu's swap entry * pool (a cluster). This might involve allocating a new cluster for current CPU * too. */ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, unsigned long *offset, unsigned long *scan_base, int order) { unsigned int nr_pages = 1 << order; struct percpu_cluster *cluster; struct swap_cluster_info *ci; unsigned int tmp, max; new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); tmp = cluster->next[order]; if (tmp == SWAP_NEXT_INVALID) { if (!cluster_list_empty(&si->free_clusters)) { tmp = cluster_next(&si->free_clusters.head) * SWAPFILE_CLUSTER; } else if (!cluster_list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ swap_do_scheduled_discard(si); *scan_base = this_cpu_read(*si->cluster_next_cpu); *offset = *scan_base; goto new_cluster; } else return false; } /* * Other CPUs can use our cluster if they can't find a free cluster, * check if there is still free entry in the cluster, maintaining * natural alignment. */ max = min_t(unsigned long, si->max, ALIGN(tmp + 1, SWAPFILE_CLUSTER)); if (tmp < max) { ci = lock_cluster(si, tmp); while (tmp < max) { if (swap_range_empty(si->swap_map, tmp, nr_pages)) break; tmp += nr_pages; } unlock_cluster(ci); } if (tmp >= max) { cluster->next[order] = SWAP_NEXT_INVALID; goto new_cluster; } *offset = tmp; *scan_base = tmp; tmp += nr_pages; cluster->next[order] = tmp < max ? tmp : SWAP_NEXT_INVALID; return true; } static void __del_from_avail_list(struct swap_info_struct *p) { int nid; assert_spin_locked(&p->lock); for_each_node(nid) plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); } static void del_from_avail_list(struct swap_info_struct *p) { spin_lock(&swap_avail_lock); __del_from_avail_list(p); spin_unlock(&swap_avail_lock); } static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned int end = offset + nr_entries - 1; if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries); if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; del_from_avail_list(si); } } static void add_to_avail_list(struct swap_info_struct *p) { int nid; spin_lock(&swap_avail_lock); for_each_node(nid) plist_add(&p->avail_lists[nid], &swap_avail_heads[nid]); spin_unlock(&swap_avail_lock); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); if (offset < si->lowest_bit) si->lowest_bit = offset; if (end > si->highest_bit) { bool was_full = !si->highest_bit; WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } clear_shadow_from_swap_cache(si->type, begin, end); /* * Make sure that try_to_unuse() observes si->inuse_pages reaching 0 * only after the above cleanups are done. */ smp_wmb(); atomic_long_add(nr_entries, &nr_swap_pages); WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries); } static void set_cluster_next(struct swap_info_struct *si, unsigned long next) { unsigned long prev; if (!(si->flags & SWP_SOLIDSTATE)) { si->cluster_next = next; return; } prev = this_cpu_read(*si->cluster_next_cpu); /* * Cross the swap address space size aligned trunk, choose * another trunk randomly to avoid lock contention on swap * address space if possible. */ if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != (next >> SWAP_ADDRESS_SPACE_SHIFT)) { /* No free swap slots available */ if (si->highest_bit <= si->lowest_bit) return; next = get_random_u32_inclusive(si->lowest_bit, si->highest_bit); next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); next = max_t(unsigned int, next, si->lowest_bit); } this_cpu_write(*si->cluster_next_cpu, next); } static bool swap_offset_available_and_locked(struct swap_info_struct *si, unsigned long offset) { if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); return true; } if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); return true; } return false; } static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[], int order) { struct swap_cluster_info *ci; unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; unsigned int nr_pages = 1 << order; int n_ret = 0; bool scanned_many = false; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ if (order > 0) { /* * Should not even be attempting large allocations when huge * page swap is disabled. Warn and fail the allocation. */ if (!IS_ENABLED(CONFIG_THP_SWAP) || nr_pages > SWAPFILE_CLUSTER) { VM_WARN_ON_ONCE(1); return 0; } /* * Swapfile is not block device or not using clusters so unable * to allocate large entries. */ if (!(si->flags & SWP_BLKDEV) || !si->cluster_info) return 0; } si->flags += SWP_SCANNING; /* * Use percpu scan base for SSD to reduce lock contention on * cluster and swap cache. For HDD, sequential access is more * important. */ if (si->flags & SWP_SOLIDSTATE) scan_base = this_cpu_read(*si->cluster_next_cpu); else scan_base = si->cluster_next; offset = scan_base; /* SSD algorithm */ if (si->cluster_info) { if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order)) { if (order > 0) goto no_page; goto scan; } } else if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info * case, just handled by scan_swap_map_try_ssd_cluster() above. */ scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ for (; last_in_cluster <= READ_ONCE(si->highest_bit); offset++) { if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; } checks: if (si->cluster_info) { while (scan_swap_map_ssd_cluster_conflict(si, offset, order)) { /* take a break if we already got some slots */ if (n_ret) goto done; if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order)) { if (order > 0) goto no_page; goto scan; } } } if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; ci = lock_cluster(si, offset); /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; unlock_cluster(ci); spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed > 0) goto checks; goto scan; /* check next one */ } if (si->swap_map[offset]) { unlock_cluster(ci); if (!n_ret) goto scan; else goto done; } memset(si->swap_map + offset, usage, nr_pages); add_cluster_info_page(si, si->cluster_info, offset, nr_pages); unlock_cluster(ci); swap_range_alloc(si, offset, nr_pages); slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ if ((n_ret == nr) || (offset >= si->highest_bit)) goto done; /* search for next available slot */ /* time to take a break? */ if (unlikely(--latency_ration < 0)) { if (n_ret) goto done; spin_unlock(&si->lock); cond_resched(); spin_lock(&si->lock); latency_ration = LATENCY_LIMIT; } /* try to get more slots in cluster */ if (si->cluster_info) { if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order)) goto checks; if (order > 0) goto done; } else if (si->cluster_nr && !si->swap_map[++offset]) { /* non-ssd case, still more slots in cluster? */ --si->cluster_nr; goto checks; } /* * Even if there's no free clusters available (fragmented), * try to scan a little more quickly with lock held unless we * have scanned too many slots already. */ if (!scanned_many) { unsigned long scan_limit; if (offset < scan_base) scan_limit = scan_base; else scan_limit = si->highest_bit; for (; offset <= scan_limit && --latency_ration > 0; offset++) { if (!si->swap_map[offset]) goto checks; } } done: if (order == 0) set_cluster_next(si, offset + 1); si->flags -= SWP_SCANNING; return n_ret; scan: VM_WARN_ON(order > 0); spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; } offset = si->lowest_bit; while (offset < scan_base) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; offset++; } spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; return n_ret; } static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) { unsigned long offset = idx * SWAPFILE_CLUSTER; struct swap_cluster_info *ci; ci = lock_cluster(si, offset); memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER); cluster_set_count_flag(ci, 0, 0); free_cluster(si, idx); unlock_cluster(ci); swap_range_free(si, offset, SWAPFILE_CLUSTER); } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order) { int order = swap_entry_order(entry_order); unsigned long size = 1 << order; struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; spin_lock(&swap_avail_lock); avail_pgs = atomic_long_read(&nr_swap_pages) / size; if (avail_pgs <= 0) { spin_unlock(&swap_avail_lock); goto noswap; } n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); atomic_long_sub(n_goal * size, &nr_swap_pages); start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); if (plist_node_empty(&si->avail_lists[node])) { spin_unlock(&si->lock); goto nextsi; } WARN(!si->highest_bit, "swap_info %d in list but !highest_bit\n", si->type); WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); __del_from_avail_list(si); spin_unlock(&si->lock); goto nextsi; } n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries, order); spin_unlock(&si->lock); if (n_ret || size > 1) goto check_out; cond_resched(); spin_lock(&swap_avail_lock); nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long)(n_goal - n_ret) * size, &nr_swap_pages); noswap: return n_ret; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; unsigned long offset; if (!entry.val) goto out; p = swp_swap_info(entry); if (!p) goto bad_nofile; if (data_race(!(p->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; if (data_race(!p->swap_map[swp_offset(entry)])) goto bad_free; return p; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p != q) { if (q != NULL) spin_unlock(&q->lock); if (p != NULL) spin_lock(&p->lock); } return p; } static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, unsigned long offset, unsigned char usage) { unsigned char count; unsigned char has_cache; count = p->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(p, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(p->swap_map[offset], usage); else WRITE_ONCE(p->swap_map[offset], SWAP_HAS_CACHE); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, RCU * reader side is locked, etc., the swap entry may become invalid * because of swapoff. Then, we need to enclose all swap related * functions with get_swap_device() and put_swap_device(), unless the * swap functions call get/put_swap_device() by themselves. * * RCU reader side lock (including any spinlock) is sufficient to * prevent swapoff, because synchronize_rcu() is called in swapoff() * before freeing data structures. * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (!percpu_ref_tryget_live(&si->users)) goto out; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(). */ smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(p, offset); usage = __swap_entry_free_locked(p, offset, 1); unlock_cluster_or_swap_info(p, ci); if (!usage) free_swap_slot(entry); return usage; } static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char count; ci = lock_cluster(p, offset); count = p->swap_map[offset]; VM_BUG_ON(count != SWAP_HAS_CACHE); p->swap_map[offset] = 0; dec_cluster_info_page(p, p->cluster_info, offset); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, 1); swap_range_free(p, offset, 1); } static void cluster_swap_free_nr(struct swap_info_struct *sis, unsigned long offset, int nr_pages) { struct swap_cluster_info *ci; DECLARE_BITMAP(to_free, BITS_PER_LONG) = { 0 }; int i, nr; ci = lock_cluster_or_swap_info(sis, offset); while (nr_pages) { nr = min(BITS_PER_LONG, nr_pages); for (i = 0; i < nr; i++) { if (!__swap_entry_free_locked(sis, offset + i, 1)) bitmap_set(to_free, i, 1); } if (!bitmap_empty(to_free, BITS_PER_LONG)) { unlock_cluster_or_swap_info(sis, ci); for_each_set_bit(i, to_free, BITS_PER_LONG) free_swap_slot(swp_entry(sis->type, offset + i)); if (nr == nr_pages) return; bitmap_clear(to_free, 0, BITS_PER_LONG); ci = lock_cluster_or_swap_info(sis, offset); } offset += nr; nr_pages -= nr; } unlock_cluster_or_swap_info(sis, ci); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free_nr(swp_entry_t entry, int nr_pages) { int nr; struct swap_info_struct *sis; unsigned long offset = swp_offset(entry); sis = _swap_info_get(entry); if (!sis) return; while (nr_pages) { nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); cluster_swap_free_nr(sis, offset, nr); offset += nr; nr_pages -= nr; } } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_folio(struct folio *folio, swp_entry_t entry) { unsigned long offset = swp_offset(entry); unsigned long idx = offset / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned char *map; unsigned int i, free_entries = 0; unsigned char val; int size = 1 << swap_entry_order(folio_order(folio)); si = _swap_info_get(entry); if (!si) return; ci = lock_cluster_or_swap_info(si, offset); if (size == SWAPFILE_CLUSTER) { map = si->swap_map + offset; for (i = 0; i < SWAPFILE_CLUSTER; i++) { val = map[i]; VM_BUG_ON(!(val & SWAP_HAS_CACHE)); if (val == SWAP_HAS_CACHE) free_entries++; } if (free_entries == SWAPFILE_CLUSTER) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER); swap_free_cluster(si, idx); spin_unlock(&si->lock); return; } } for (i = 0; i < size; i++, entry.val++) { if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { unlock_cluster_or_swap_info(si, ci); free_swap_slot(entry); if (i == size - 1) return; lock_cluster_or_swap_info(si, offset); } } unlock_cluster_or_swap_info(si, ci); } static int swp_entry_cmp(const void *ent1, const void *ent2) { const swp_entry_t *e1 = ent1, *e2 = ent2; return (int)swp_type(*e1) - (int)swp_type(*e2); } void swapcache_free_entries(swp_entry_t *entries, int n) { struct swap_info_struct *p, *prev; int i; if (n <= 0) return; prev = NULL; p = NULL; /* * Sort swap entries by swap device, so each lock is only taken once. * nr_swapfiles isn't absolutely correct, but the overhead of sort() is * so low that it isn't necessary to optimize further. */ if (nr_swapfiles > 1) sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); for (i = 0; i < n; ++i) { p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_free(p, entries[i]); prev = p; } if (p) spin_unlock(&p->lock); } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si = swp_swap_info(entry); pgoff_t offset = swp_offset(entry); return swap_count(si->swap_map[offset]); } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; int count; ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster_or_swap_info(si, ci); return count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *p; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; p = _swap_info_get(entry); if (!p) return 0; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(p->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_local_page(page); tmp_count = map[offset]; kunmap_local(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster_or_swap_info(p, ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry, int order) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned int nr_pages = 1 << order; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, nr_pages); int i; bool ret = false; ci = lock_cluster_or_swap_info(si, offset); if (!ci || nr_pages == 1) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < nr_pages; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster_or_swap_info(si, ci); return ret; } static bool folio_swapped(struct folio *folio) { swp_entry_t entry = folio->swap; struct swap_info_struct *si = _swap_info_get(entry); if (!si) return false; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_swapcount(si, entry) != 0; return swap_page_trans_huge_swapped(si, entry, folio_order(folio)); } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; if (folio_swapped(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; delete_from_swap_cache(folio); folio_set_dirty(folio); return true; } /** * free_swap_and_cache_nr() - Release reference on range of swap entries and * reclaim their cache if no more references remain. * @entry: First entry of range. * @nr: Number of entries in range. * * For each swap entry in the contiguous range, release a reference. If any swap * entries become free, try to reclaim their underlying folios, if present. The * offset range is defined by [entry.offset, entry.offset + nr). */ void free_swap_and_cache_nr(swp_entry_t entry, int nr) { const unsigned long start_offset = swp_offset(entry); const unsigned long end_offset = start_offset + nr; unsigned int type = swp_type(entry); struct swap_info_struct *si; bool any_only_cache = false; unsigned long offset; unsigned char count; if (non_swap_entry(entry)) return; si = get_swap_device(entry); if (!si) return; if (WARN_ON(end_offset > si->max)) goto out; /* * First free all entries in the range. */ for (offset = start_offset; offset < end_offset; offset++) { if (data_race(si->swap_map[offset])) { count = __swap_entry_free(si, swp_entry(type, offset)); if (count == SWAP_HAS_CACHE) any_only_cache = true; } else { WARN_ON_ONCE(1); } } /* * Short-circuit the below loop if none of the entries had their * reference drop to zero. */ if (!any_only_cache) goto out; /* * Now go back over the range trying to reclaim the swap cache. This is * more efficient for large folios because we will only try to reclaim * the swap once per folio in the common case. If we do * __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the * latter will get a reference and lock the folio for every individual * page but will only succeed once the swap slot for every subpage is * zero. */ for (offset = start_offset; offset < end_offset; offset += nr) { nr = 1; if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { /* * Folios are always naturally aligned in swap so * advance forward to the next boundary. Zero means no * folio was found for the swap entry, so advance by 1 * in this case. Negative value means folio was found * but could not be reclaimed. Here we can still advance * to the next boundary. */ nr = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); if (nr == 0) nr = 1; else if (nr < 0) nr = -nr; nr = ALIGN(offset + 1, nr) - offset; } } out: put_swap_device(si); } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ spin_lock(&si->lock); if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0)) atomic_long_dec(&nr_swap_pages); spin_unlock(&si->lock); fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_swap_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page; struct folio *swapcache; spinlock_t *ptl; pte_t *pte, new_pte, old_pte; bool hwpoisoned = false; int ret = 1; swapcache = folio; folio = ksm_might_need_to_copy(folio, vma, addr); if (unlikely(!folio)) return -ENOMEM; else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { hwpoisoned = true; folio = swapcache; } page = folio_file_page(folio, swp_offset(entry)); if (PageHWPoison(page)) hwpoisoned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), swp_entry_to_pte(entry)))) { ret = 0; goto out; } old_pte = ptep_get(pte); if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) { swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); if (hwpoisoned) { swp_entry = make_hwpoison_entry(page); } else { swp_entry = make_poisoned_swp_entry(); } new_pte = swp_entry_to_pte(swp_entry); ret = 0; goto setpte; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); folio_get(folio); if (folio == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): writeback would be problematic. * However, we do a folio_wait_writeback() just before this * call and have the folio locked. */ VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (pte_swp_exclusive(old_pte)) rmap_flags |= RMAP_EXCLUSIVE; /* * We currently only expect small !anon folios, which are either * fully exclusive or fully shared. If we ever get large folios * here, we have to be careful. */ if (!folio_test_anon(folio)) { VM_WARN_ON_ONCE(folio_test_large(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, addr, rmap_flags); } else { folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); } } else { /* ksm created a completely new copy */ folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(old_pte)) new_pte = pte_mkuffd_wp(new_pte); setpte: set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: if (pte) pte_unmap_unlock(pte, ptl); if (folio != swapcache) { folio_unlock(folio); folio_put(folio); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { pte_t *pte = NULL; struct swap_info_struct *si; si = swap_info[type]; do { struct folio *folio; unsigned long offset; unsigned char swp_count; swp_entry_t entry; int ret; pte_t ptent; if (!pte++) { pte = pte_offset_map(pmd, addr); if (!pte) break; } ptent = ptep_get_lockless(pte); if (!is_swap_pte(ptent)) continue; entry = pte_to_swp_entry(ptent); if (swp_type(entry) != type) continue; offset = swp_offset(entry); pte_unmap(pte); pte = NULL; folio = swap_cache_get_folio(entry, vma, addr); if (!folio) { struct page *page; struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); if (page) folio = page_folio(page); } if (!folio) { swp_count = READ_ONCE(si->swap_map[offset]); if (swp_count == 0 || swp_count == SWAP_MAP_BAD) continue; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); return ret; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } while (addr += PAGE_SIZE, addr != end); if (pte) pte_unmap(pte); return 0; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (vma->anon_vma) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } mmap_read_unlock(mm); return ret; } /* * Scan swap_map from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!READ_ONCE(si->inuse_pages)) goto success; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry)); if (IS_ERR(folio)) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writepage() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; return -EINTR; } success: /* * Make sure that further cleanups after try_to_unuse() returns happen * after swap_range_free() reduces si->inuse_pages to 0. */ smp_mb(); return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_read_folio * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *p) { struct block_device *bdev; if (p->bdev) bdev = p->bdev; else bdev = p->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { int i; if (prio >= 0) p->prio = prio; else p->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ p->list.prio = -p->prio; for_each_node(i) { if (p->prio >= 0) p->avail_lists[i].prio = -p->prio; else { if (swap_node(p) == i) p->avail_lists[i].prio = 1; else p->avail_lists[i].prio = -p->prio; } } p->swap_map = swap_map; p->cluster_info = cluster_info; } static void _enable_swap_info(struct swap_info_struct *p) { p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&p->list, &swap_active_head); /* add to available list iff swap device is not full */ if (p->highest_bit) add_to_avail_list(p); } static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, prio, swap_map, cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&p->users); spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, p->prio, p->swap_map, p->cluster_info); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } static bool __has_usable_swap(void) { return !plist_head_empty(&swap_active_head); } bool has_usable_swap(void) { bool ret; spin_lock(&swap_lock); ret = __has_usable_swap(); spin_unlock(&swap_lock); return ret; } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); /* * Wait for swap operations protected by get/put_swap_device() * to complete. Because of synchronize_rcu() here, all swap * operations protected by RCU reader side lock (including any * spinlock) will be waited too. This makes it easy to * prevent folio_test_swapcache() and the following swap cache * operations from racing with swapoff. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); spin_lock(&p->lock); } swap_file = p->swap_file; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); zswap_swapoff(p->type); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; vfree(swap_map); kvfree(cluster_info); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = K(si->pages); inuse = K(READ_ONCE(si->inuse_pages)); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) { if (S_ISBLK(inode->i_mode)) { p->bdev = I_BDEV(inode); /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(p->bdev)) return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *p, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } p->lowest_bit = 1; p->cluster_next = 1; p->cluster_nr = 0; maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", K(maxpages), K(last_page)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } p->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long maxpages, sector_t *span) { unsigned int j, k; unsigned int nr_good_pages; int nr_extents; unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); unsigned long col = p->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; unsigned long i, idx; nr_good_pages = maxpages - 1; /* omit header page */ cluster_list_init(&p->free_clusters); cluster_list_init(&p->discard_clusters); for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; /* * Haven't marked the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, page_nr); } } /* Haven't marked the cluster free yet, no list operation involved */ for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(p, cluster_info, i); if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; /* * Not mark the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, 0); p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, span); if (nr_extents < 0) return nr_extents; nr_good_pages = p->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } if (!cluster_info) return nr_extents; /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { idx = i * SWAP_CLUSTER_COLS + j; if (idx >= nr_clusters) continue; if (cluster_count(&cluster_info[idx])) continue; cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); cluster_list_add_tail(&p->free_clusters, cluster_info, idx); } } return nr_extents; } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; struct swap_cluster_info *cluster_info = NULL; struct page *page = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; p = alloc_swap_info(); if (IS_ERR(p)) return PTR_ERR(p); INIT_WORK(&p->discard_work, swap_discard_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } p->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(p, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } page = read_mapping_page(mapping, 0, swap_file); if (IS_ERR(page)) { error = PTR_ERR(page); goto bad_swap_unlock_inode; } swap_header = kmap(page); maxpages = read_swap_header(p, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (p->bdev && bdev_stable_writes(p->bdev)) p->flags |= SWP_STABLE_WRITES; if (p->bdev && bdev_synchronous(p->bdev)) p->flags |= SWP_SYNCHRONOUS_IO; if (p->bdev && bdev_nonrot(p->bdev)) { int cpu, i; unsigned long ci, nr_cluster; p->flags |= SWP_SOLIDSTATE; p->cluster_next_cpu = alloc_percpu(unsigned int); if (!p->cluster_next_cpu) { error = -ENOMEM; goto bad_swap_unlock_inode; } /* * select a random position to start with to help wear leveling * SSD */ for_each_possible_cpu(cpu) { per_cpu(*p->cluster_next_cpu, cpu) = get_random_u32_inclusive(1, p->highest_bit); } nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); cluster_info = kvcalloc(nr_cluster, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) { error = -ENOMEM; goto bad_swap_unlock_inode; } for (ci = 0; ci < nr_cluster; ci++) spin_lock_init(&((cluster_info + ci)->lock)); p->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!p->percpu_cluster) { error = -ENOMEM; goto bad_swap_unlock_inode; } for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(p->percpu_cluster, cpu); for (i = 0; i < SWAP_NR_ORDERS; i++) cluster->next[i] = SWAP_NEXT_INVALID; } } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } error = swap_cgroup_swapon(p->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } if ((swap_flags & SWAP_FLAG_DISCARD) && p->bdev && bdev_max_discard_sectors(p->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) p->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) p->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (p->flags & SWP_AREA_DISCARD) { int err = discard_swap(p); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", p, err); } } error = init_swap_address_space(p->type, maxpages); if (error) goto bad_swap_unlock_inode; error = zswap_swapon(p->type, maxpages); if (error) goto free_swap_address_space; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_zswap; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(p, prio, swap_map, cluster_info); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", K(p->pages), name->name, p->prio, nr_extents, K((unsigned long long)span), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", (p->flags & SWP_DISCARDABLE) ? "D" : "", (p->flags & SWP_AREA_DISCARD) ? "s" : "", (p->flags & SWP_PAGE_DISCARD) ? "c" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_zswap: zswap_swapoff(p->type); free_swap_address_space: exit_swap_address_space(p->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; inode = NULL; destroy_swap_extents(p); swap_cgroup_swapoff(p->type); spin_lock(&swap_lock); p->swap_file = NULL; p->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(cluster_info); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (page && !IS_ERR(page)) { kunmap(page); put_page(page); } if (name) putname(name); if (inode) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += READ_ONCE(si->inuse_pages); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that a swap entry is valid and increment its swap map count. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) { struct swap_info_struct *p; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err; p = swp_swap_info(entry); offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = p->swap_map[offset]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; err = 0; if (usage == SWAP_HAS_CACHE) { /* set SWAP_HAS_CACHE if there is no cache and entry is used */ if (!has_cache && count) has_cache = SWAP_HAS_CACHE; else if (has_cache) /* someone else added cache */ err = -EEXIST; else /* no users remaining */ err = -ENOENT; } else if (count || has_cache) { if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) err = -EINVAL; else if (swap_count_continued(p, offset, count)) count = COUNT_CONTINUED; else err = -ENOMEM; } else err = -ENOENT; /* unused swap entry */ if (!err) WRITE_ONCE(p->swap_map[offset], count | has_cache); unlock_out: unlock_cluster_or_swap_info(p, ci); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry) { __swap_duplicate(entry, SWAP_MAP_SHMEM); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: swap entry for which we allocate swap cache. * * Called when allocating swap cache for existing swap entry, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry) { return __swap_duplicate(entry, SWAP_HAS_CACHE); } void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(si, offset); usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); unlock_cluster_or_swap_info(si, ci); if (!usage) free_swap_slot(entry); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); } /* * out-of-line methods to avoid include hell. */ struct address_space *swapcache_mapping(struct folio *folio) { return swp_swap_info(folio->swap)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(swapcache_mapping); pgoff_t __folio_swap_cache_index(struct folio *folio) { return swap_cache_index(folio->swap); } EXPORT_SYMBOL_GPL(__folio_swap_cache_index); /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } spin_lock(&si->lock); offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_local_page(list_page) + offset; count = *map; kunmap_local(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); spin_unlock(&si->lock); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster * lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_local_page(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_local(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_local_page(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = COUNT_CONTINUED; kunmap_local(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_local(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { struct swap_info_struct *si, *next; int nid = folio_nid(folio); if (!(gfp & __GFP_IO)) return; if (!__has_usable_swap()) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_disk) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); swapfile_maximum_size = arch_max_swapfile_size(); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008-2011, Intel Corporation. * * Description: Data Center Bridging netlink interface * Author: Lucy Liu <lucy.liu@intel.com> */ #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/slab.h> #include <net/netlink.h> #include <net/rtnetlink.h> #include <linux/dcbnl.h> #include <net/dcbevent.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <net/sock.h> /* Data Center Bridging (DCB) is a collection of Ethernet enhancements * intended to allow network traffic with differing requirements * (highly reliable, no drops vs. best effort vs. low latency) to operate * and co-exist on Ethernet. Current DCB features are: * * Enhanced Transmission Selection (aka Priority Grouping [PG]) - provides a * framework for assigning bandwidth guarantees to traffic classes. * * Priority-based Flow Control (PFC) - provides a flow control mechanism which * can work independently for each 802.1p priority. * * Congestion Notification - provides a mechanism for end-to-end congestion * control for protocols which do not have built-in congestion management. * * More information about the emerging standards for these Ethernet features * can be found at: http://www.ieee802.org/1/pages/dcbridges.html * * This file implements an rtnetlink interface to allow configuration of DCB * features for capable devices. */ /**************** DCB attribute policies *************************************/ /* DCB netlink attributes policy */ static const struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = { [DCB_ATTR_IFNAME] = {.type = NLA_NUL_STRING, .len = IFNAMSIZ - 1}, [DCB_ATTR_STATE] = {.type = NLA_U8}, [DCB_ATTR_PFC_CFG] = {.type = NLA_NESTED}, [DCB_ATTR_PG_CFG] = {.type = NLA_NESTED}, [DCB_ATTR_SET_ALL] = {.type = NLA_U8}, [DCB_ATTR_PERM_HWADDR] = {.type = NLA_FLAG}, [DCB_ATTR_CAP] = {.type = NLA_NESTED}, [DCB_ATTR_PFC_STATE] = {.type = NLA_U8}, [DCB_ATTR_BCN] = {.type = NLA_NESTED}, [DCB_ATTR_APP] = {.type = NLA_NESTED}, [DCB_ATTR_IEEE] = {.type = NLA_NESTED}, [DCB_ATTR_DCBX] = {.type = NLA_U8}, [DCB_ATTR_FEATCFG] = {.type = NLA_NESTED}, }; /* DCB priority flow control to User Priority nested attributes */ static const struct nla_policy dcbnl_pfc_up_nest[DCB_PFC_UP_ATTR_MAX + 1] = { [DCB_PFC_UP_ATTR_0] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_1] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_2] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_3] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_4] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_5] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_6] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_7] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_ALL] = {.type = NLA_FLAG}, }; /* DCB priority grouping nested attributes */ static const struct nla_policy dcbnl_pg_nest[DCB_PG_ATTR_MAX + 1] = { [DCB_PG_ATTR_TC_0] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_1] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_2] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_3] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_4] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_5] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_6] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_7] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_ALL] = {.type = NLA_NESTED}, [DCB_PG_ATTR_BW_ID_0] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_1] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_2] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_3] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_4] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_5] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_6] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_7] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_ALL] = {.type = NLA_FLAG}, }; /* DCB traffic class nested attributes. */ static const struct nla_policy dcbnl_tc_param_nest[DCB_TC_ATTR_PARAM_MAX + 1] = { [DCB_TC_ATTR_PARAM_PGID] = {.type = NLA_U8}, [DCB_TC_ATTR_PARAM_UP_MAPPING] = {.type = NLA_U8}, [DCB_TC_ATTR_PARAM_STRICT_PRIO] = {.type = NLA_U8}, [DCB_TC_ATTR_PARAM_BW_PCT] = {.type = NLA_U8}, [DCB_TC_ATTR_PARAM_ALL] = {.type = NLA_FLAG}, }; /* DCB capabilities nested attributes. */ static const struct nla_policy dcbnl_cap_nest[DCB_CAP_ATTR_MAX + 1] = { [DCB_CAP_ATTR_ALL] = {.type = NLA_FLAG}, [DCB_CAP_ATTR_PG] = {.type = NLA_U8}, [DCB_CAP_ATTR_PFC] = {.type = NLA_U8}, [DCB_CAP_ATTR_UP2TC] = {.type = NLA_U8}, [DCB_CAP_ATTR_PG_TCS] = {.type = NLA_U8}, [DCB_CAP_ATTR_PFC_TCS] = {.type = NLA_U8}, [DCB_CAP_ATTR_GSP] = {.type = NLA_U8}, [DCB_CAP_ATTR_BCN] = {.type = NLA_U8}, [DCB_CAP_ATTR_DCBX] = {.type = NLA_U8}, }; /* DCB capabilities nested attributes. */ static const struct nla_policy dcbnl_numtcs_nest[DCB_NUMTCS_ATTR_MAX + 1] = { [DCB_NUMTCS_ATTR_ALL] = {.type = NLA_FLAG}, [DCB_NUMTCS_ATTR_PG] = {.type = NLA_U8}, [DCB_NUMTCS_ATTR_PFC] = {.type = NLA_U8}, }; /* DCB BCN nested attributes. */ static const struct nla_policy dcbnl_bcn_nest[DCB_BCN_ATTR_MAX + 1] = { [DCB_BCN_ATTR_RP_0] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_1] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_2] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_3] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_4] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_5] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_6] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_7] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_ALL] = {.type = NLA_FLAG}, [DCB_BCN_ATTR_BCNA_0] = {.type = NLA_U32}, [DCB_BCN_ATTR_BCNA_1] = {.type = NLA_U32}, [DCB_BCN_ATTR_ALPHA] = {.type = NLA_U32}, [DCB_BCN_ATTR_BETA] = {.type = NLA_U32}, [DCB_BCN_ATTR_GD] = {.type = NLA_U32}, [DCB_BCN_ATTR_GI] = {.type = NLA_U32}, [DCB_BCN_ATTR_TMAX] = {.type = NLA_U32}, [DCB_BCN_ATTR_TD] = {.type = NLA_U32}, [DCB_BCN_ATTR_RMIN] = {.type = NLA_U32}, [DCB_BCN_ATTR_W] = {.type = NLA_U32}, [DCB_BCN_ATTR_RD] = {.type = NLA_U32}, [DCB_BCN_ATTR_RU] = {.type = NLA_U32}, [DCB_BCN_ATTR_WRTT] = {.type = NLA_U32}, [DCB_BCN_ATTR_RI] = {.type = NLA_U32}, [DCB_BCN_ATTR_C] = {.type = NLA_U32}, [DCB_BCN_ATTR_ALL] = {.type = NLA_FLAG}, }; /* DCB APP nested attributes. */ static const struct nla_policy dcbnl_app_nest[DCB_APP_ATTR_MAX + 1] = { [DCB_APP_ATTR_IDTYPE] = {.type = NLA_U8}, [DCB_APP_ATTR_ID] = {.type = NLA_U16}, [DCB_APP_ATTR_PRIORITY] = {.type = NLA_U8}, }; /* IEEE 802.1Qaz nested attributes. */ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { [DCB_ATTR_IEEE_ETS] = {.len = sizeof(struct ieee_ets)}, [DCB_ATTR_IEEE_PFC] = {.len = sizeof(struct ieee_pfc)}, [DCB_ATTR_IEEE_APP_TABLE] = {.type = NLA_NESTED}, [DCB_ATTR_IEEE_MAXRATE] = {.len = sizeof(struct ieee_maxrate)}, [DCB_ATTR_IEEE_QCN] = {.len = sizeof(struct ieee_qcn)}, [DCB_ATTR_IEEE_QCN_STATS] = {.len = sizeof(struct ieee_qcn_stats)}, [DCB_ATTR_DCB_BUFFER] = {.len = sizeof(struct dcbnl_buffer)}, [DCB_ATTR_DCB_APP_TRUST_TABLE] = {.type = NLA_NESTED}, }; /* DCB number of traffic classes nested attributes. */ static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { [DCB_FEATCFG_ATTR_ALL] = {.type = NLA_FLAG}, [DCB_FEATCFG_ATTR_PG] = {.type = NLA_U8}, [DCB_FEATCFG_ATTR_PFC] = {.type = NLA_U8}, [DCB_FEATCFG_ATTR_APP] = {.type = NLA_U8}, }; static LIST_HEAD(dcb_app_list); static LIST_HEAD(dcb_rewr_list); static DEFINE_SPINLOCK(dcb_lock); static enum ieee_attrs_app dcbnl_app_attr_type_get(u8 selector) { switch (selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: case IEEE_8021QAZ_APP_SEL_STREAM: case IEEE_8021QAZ_APP_SEL_DGRAM: case IEEE_8021QAZ_APP_SEL_ANY: case IEEE_8021QAZ_APP_SEL_DSCP: return DCB_ATTR_IEEE_APP; case DCB_APP_SEL_PCP: return DCB_ATTR_DCB_APP; default: return DCB_ATTR_IEEE_APP_UNSPEC; } } static bool dcbnl_app_attr_type_validate(enum ieee_attrs_app type) { switch (type) { case DCB_ATTR_IEEE_APP: case DCB_ATTR_DCB_APP: return true; default: return false; } } static bool dcbnl_app_selector_validate(enum ieee_attrs_app type, u8 selector) { return dcbnl_app_attr_type_get(selector) == type; } static struct sk_buff *dcbnl_newmsg(int type, u8 cmd, u32 port, u32 seq, u32 flags, struct nlmsghdr **nlhp) { struct sk_buff *skb; struct dcbmsg *dcb; struct nlmsghdr *nlh; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return NULL; nlh = nlmsg_put(skb, port, seq, type, sizeof(*dcb), flags); BUG_ON(!nlh); dcb = nlmsg_data(nlh); dcb->dcb_family = AF_UNSPEC; dcb->cmd = cmd; dcb->dcb_pad = 0; if (nlhp) *nlhp = nlh; return skb; } static int dcbnl_getstate(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { /* if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->getstate) */ if (!netdev->dcbnl_ops->getstate) return -EOPNOTSUPP; return nla_put_u8(skb, DCB_ATTR_STATE, netdev->dcbnl_ops->getstate(netdev)); } static int dcbnl_getpfccfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1], *nest; u8 value; int ret; int i; int getall = 0; if (!tb[DCB_ATTR_PFC_CFG]) return -EINVAL; if (!netdev->dcbnl_ops->getpfccfg) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_PFC_UP_ATTR_MAX, tb[DCB_ATTR_PFC_CFG], dcbnl_pfc_up_nest, NULL); if (ret) return ret; nest = nla_nest_start_noflag(skb, DCB_ATTR_PFC_CFG); if (!nest) return -EMSGSIZE; if (data[DCB_PFC_UP_ATTR_ALL]) getall = 1; for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { if (!getall && !data[i]) continue; netdev->dcbnl_ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0, &value); ret = nla_put_u8(skb, i, value); if (ret) { nla_nest_cancel(skb, nest); return ret; } } nla_nest_end(skb, nest); return 0; } static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { u8 perm_addr[MAX_ADDR_LEN]; if (!netdev->dcbnl_ops->getpermhwaddr) return -EOPNOTSUPP; memset(perm_addr, 0, sizeof(perm_addr)); netdev->dcbnl_ops->getpermhwaddr(netdev, perm_addr); return nla_put(skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr), perm_addr); } static int dcbnl_getcap(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_CAP_ATTR_MAX + 1], *nest; u8 value; int ret; int i; int getall = 0; if (!tb[DCB_ATTR_CAP]) return -EINVAL; if (!netdev->dcbnl_ops->getcap) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_CAP_ATTR_MAX, tb[DCB_ATTR_CAP], dcbnl_cap_nest, NULL); if (ret) return ret; nest = nla_nest_start_noflag(skb, DCB_ATTR_CAP); if (!nest) return -EMSGSIZE; if (data[DCB_CAP_ATTR_ALL]) getall = 1; for (i = DCB_CAP_ATTR_ALL+1; i <= DCB_CAP_ATTR_MAX; i++) { if (!getall && !data[i]) continue; if (!netdev->dcbnl_ops->getcap(netdev, i, &value)) { ret = nla_put_u8(skb, i, value); if (ret) { nla_nest_cancel(skb, nest); return ret; } } } nla_nest_end(skb, nest); return 0; } static int dcbnl_getnumtcs(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1], *nest; u8 value; int ret; int i; int getall = 0; if (!tb[DCB_ATTR_NUMTCS]) return -EINVAL; if (!netdev->dcbnl_ops->getnumtcs) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS], dcbnl_numtcs_nest, NULL); if (ret) return ret; nest = nla_nest_start_noflag(skb, DCB_ATTR_NUMTCS); if (!nest) return -EMSGSIZE; if (data[DCB_NUMTCS_ATTR_ALL]) getall = 1; for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) { if (!getall && !data[i]) continue; ret = netdev->dcbnl_ops->getnumtcs(netdev, i, &value); if (!ret) { ret = nla_put_u8(skb, i, value); if (ret) { nla_nest_cancel(skb, nest); return ret; } } else return -EINVAL; } nla_nest_end(skb, nest); return 0; } static int dcbnl_setnumtcs(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1]; int ret; u8 value; int i; if (!tb[DCB_ATTR_NUMTCS]) return -EINVAL; if (!netdev->dcbnl_ops->setnumtcs) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS], dcbnl_numtcs_nest, NULL); if (ret) return ret; for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) { if (data[i] == NULL) continue; value = nla_get_u8(data[i]); ret = netdev->dcbnl_ops->setnumtcs(netdev, i, value); if (ret) break; } return nla_put_u8(skb, DCB_ATTR_NUMTCS, !!ret); } static int dcbnl_getpfcstate(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { if (!netdev->dcbnl_ops->getpfcstate) return -EOPNOTSUPP; return nla_put_u8(skb, DCB_ATTR_PFC_STATE, netdev->dcbnl_ops->getpfcstate(netdev)); } static int dcbnl_setpfcstate(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { u8 value; if (!tb[DCB_ATTR_PFC_STATE]) return -EINVAL; if (!netdev->dcbnl_ops->setpfcstate) return -EOPNOTSUPP; value = nla_get_u8(tb[DCB_ATTR_PFC_STATE]); netdev->dcbnl_ops->setpfcstate(netdev, value); return nla_put_u8(skb, DCB_ATTR_PFC_STATE, 0); } static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *app_nest; struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; u16 id; u8 up, idtype; int ret; if (!tb[DCB_ATTR_APP]) return -EINVAL; ret = nla_parse_nested_deprecated(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], dcbnl_app_nest, NULL); if (ret) return ret; /* all must be non-null */ if ((!app_tb[DCB_APP_ATTR_IDTYPE]) || (!app_tb[DCB_APP_ATTR_ID])) return -EINVAL; /* either by eth type or by socket number */ idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]); if ((idtype != DCB_APP_IDTYPE_ETHTYPE) && (idtype != DCB_APP_IDTYPE_PORTNUM)) return -EINVAL; id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); if (netdev->dcbnl_ops->getapp) { ret = netdev->dcbnl_ops->getapp(netdev, idtype, id); if (ret < 0) return ret; else up = ret; } else { struct dcb_app app = { .selector = idtype, .protocol = id, }; up = dcb_getapp(netdev, &app); } app_nest = nla_nest_start_noflag(skb, DCB_ATTR_APP); if (!app_nest) return -EMSGSIZE; ret = nla_put_u8(skb, DCB_APP_ATTR_IDTYPE, idtype); if (ret) goto out_cancel; ret = nla_put_u16(skb, DCB_APP_ATTR_ID, id); if (ret) goto out_cancel; ret = nla_put_u8(skb, DCB_APP_ATTR_PRIORITY, up); if (ret) goto out_cancel; nla_nest_end(skb, app_nest); return 0; out_cancel: nla_nest_cancel(skb, app_nest); return ret; } static int dcbnl_setapp(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { int ret; u16 id; u8 up, idtype; struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; if (!tb[DCB_ATTR_APP]) return -EINVAL; ret = nla_parse_nested_deprecated(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], dcbnl_app_nest, NULL); if (ret) return ret; /* all must be non-null */ if ((!app_tb[DCB_APP_ATTR_IDTYPE]) || (!app_tb[DCB_APP_ATTR_ID]) || (!app_tb[DCB_APP_ATTR_PRIORITY])) return -EINVAL; /* either by eth type or by socket number */ idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]); if ((idtype != DCB_APP_IDTYPE_ETHTYPE) && (idtype != DCB_APP_IDTYPE_PORTNUM)) return -EINVAL; id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); up = nla_get_u8(app_tb[DCB_APP_ATTR_PRIORITY]); if (netdev->dcbnl_ops->setapp) { ret = netdev->dcbnl_ops->setapp(netdev, idtype, id, up); if (ret < 0) return ret; } else { struct dcb_app app; app.selector = idtype; app.protocol = id; app.priority = up; ret = dcb_setapp(netdev, &app); } ret = nla_put_u8(skb, DCB_ATTR_APP, ret); dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SAPP, seq, 0); return ret; } static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, struct nlattr **tb, struct sk_buff *skb, int dir) { struct nlattr *pg_nest, *param_nest, *data; struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1]; struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1]; u8 prio, pgid, tc_pct, up_map; int ret; int getall = 0; int i; if (!tb[DCB_ATTR_PG_CFG]) return -EINVAL; if (!netdev->dcbnl_ops->getpgtccfgtx || !netdev->dcbnl_ops->getpgtccfgrx || !netdev->dcbnl_ops->getpgbwgcfgtx || !netdev->dcbnl_ops->getpgbwgcfgrx) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(pg_tb, DCB_PG_ATTR_MAX, tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest, NULL); if (ret) return ret; pg_nest = nla_nest_start_noflag(skb, DCB_ATTR_PG_CFG); if (!pg_nest) return -EMSGSIZE; if (pg_tb[DCB_PG_ATTR_TC_ALL]) getall = 1; for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { if (!getall && !pg_tb[i]) continue; if (pg_tb[DCB_PG_ATTR_TC_ALL]) data = pg_tb[DCB_PG_ATTR_TC_ALL]; else data = pg_tb[i]; ret = nla_parse_nested_deprecated(param_tb, DCB_TC_ATTR_PARAM_MAX, data, dcbnl_tc_param_nest, NULL); if (ret) goto err_pg; param_nest = nla_nest_start_noflag(skb, i); if (!param_nest) goto err_pg; pgid = DCB_ATTR_VALUE_UNDEFINED; prio = DCB_ATTR_VALUE_UNDEFINED; tc_pct = DCB_ATTR_VALUE_UNDEFINED; up_map = DCB_ATTR_VALUE_UNDEFINED; if (dir) { /* Rx */ netdev->dcbnl_ops->getpgtccfgrx(netdev, i - DCB_PG_ATTR_TC_0, &prio, &pgid, &tc_pct, &up_map); } else { /* Tx */ netdev->dcbnl_ops->getpgtccfgtx(netdev, i - DCB_PG_ATTR_TC_0, &prio, &pgid, &tc_pct, &up_map); } if (param_tb[DCB_TC_ATTR_PARAM_PGID] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_PGID, pgid); if (ret) goto err_param; } if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map); if (ret) goto err_param; } if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio); if (ret) goto err_param; } if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct); if (ret) goto err_param; } nla_nest_end(skb, param_nest); } if (pg_tb[DCB_PG_ATTR_BW_ID_ALL]) getall = 1; else getall = 0; for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) { if (!getall && !pg_tb[i]) continue; tc_pct = DCB_ATTR_VALUE_UNDEFINED; if (dir) { /* Rx */ netdev->dcbnl_ops->getpgbwgcfgrx(netdev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); } else { /* Tx */ netdev->dcbnl_ops->getpgbwgcfgtx(netdev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); } ret = nla_put_u8(skb, i, tc_pct); if (ret) goto err_pg; } nla_nest_end(skb, pg_nest); return 0; err_param: nla_nest_cancel(skb, param_nest); err_pg: nla_nest_cancel(skb, pg_nest); return -EMSGSIZE; } static int dcbnl_pgtx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 0); } static int dcbnl_pgrx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 1); } static int dcbnl_setstate(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { u8 value; if (!tb[DCB_ATTR_STATE]) return -EINVAL; if (!netdev->dcbnl_ops->setstate) return -EOPNOTSUPP; value = nla_get_u8(tb[DCB_ATTR_STATE]); return nla_put_u8(skb, DCB_ATTR_STATE, netdev->dcbnl_ops->setstate(netdev, value)); } static int dcbnl_setpfccfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1]; int i; int ret; u8 value; if (!tb[DCB_ATTR_PFC_CFG]) return -EINVAL; if (!netdev->dcbnl_ops->setpfccfg) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_PFC_UP_ATTR_MAX, tb[DCB_ATTR_PFC_CFG], dcbnl_pfc_up_nest, NULL); if (ret) return ret; for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { if (data[i] == NULL) continue; value = nla_get_u8(data[i]); netdev->dcbnl_ops->setpfccfg(netdev, data[i]->nla_type - DCB_PFC_UP_ATTR_0, value); } return nla_put_u8(skb, DCB_ATTR_PFC_CFG, 0); } static int dcbnl_setall(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { int ret; if (!tb[DCB_ATTR_SET_ALL]) return -EINVAL; if (!netdev->dcbnl_ops->setall) return -EOPNOTSUPP; ret = nla_put_u8(skb, DCB_ATTR_SET_ALL, netdev->dcbnl_ops->setall(netdev)); dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SET_ALL, seq, 0); return ret; } static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb, int dir) { struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1]; struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1]; int ret; int i; u8 pgid; u8 up_map; u8 prio; u8 tc_pct; if (!tb[DCB_ATTR_PG_CFG]) return -EINVAL; if (!netdev->dcbnl_ops->setpgtccfgtx || !netdev->dcbnl_ops->setpgtccfgrx || !netdev->dcbnl_ops->setpgbwgcfgtx || !netdev->dcbnl_ops->setpgbwgcfgrx) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(pg_tb, DCB_PG_ATTR_MAX, tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest, NULL); if (ret) return ret; for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { if (!pg_tb[i]) continue; ret = nla_parse_nested_deprecated(param_tb, DCB_TC_ATTR_PARAM_MAX, pg_tb[i], dcbnl_tc_param_nest, NULL); if (ret) return ret; pgid = DCB_ATTR_VALUE_UNDEFINED; prio = DCB_ATTR_VALUE_UNDEFINED; tc_pct = DCB_ATTR_VALUE_UNDEFINED; up_map = DCB_ATTR_VALUE_UNDEFINED; if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO]) prio = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO]); if (param_tb[DCB_TC_ATTR_PARAM_PGID]) pgid = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_PGID]); if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT]) tc_pct = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_BW_PCT]); if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING]) up_map = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING]); /* dir: Tx = 0, Rx = 1 */ if (dir) { /* Rx */ netdev->dcbnl_ops->setpgtccfgrx(netdev, i - DCB_PG_ATTR_TC_0, prio, pgid, tc_pct, up_map); } else { /* Tx */ netdev->dcbnl_ops->setpgtccfgtx(netdev, i - DCB_PG_ATTR_TC_0, prio, pgid, tc_pct, up_map); } } for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) { if (!pg_tb[i]) continue; tc_pct = nla_get_u8(pg_tb[i]); /* dir: Tx = 0, Rx = 1 */ if (dir) { /* Rx */ netdev->dcbnl_ops->setpgbwgcfgrx(netdev, i - DCB_PG_ATTR_BW_ID_0, tc_pct); } else { /* Tx */ netdev->dcbnl_ops->setpgbwgcfgtx(netdev, i - DCB_PG_ATTR_BW_ID_0, tc_pct); } } return nla_put_u8(skb, DCB_ATTR_PG_CFG, 0); } static int dcbnl_pgtx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 0); } static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 1); } static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *bcn_nest; struct nlattr *bcn_tb[DCB_BCN_ATTR_MAX + 1]; u8 value_byte; u32 value_integer; int ret; bool getall = false; int i; if (!tb[DCB_ATTR_BCN]) return -EINVAL; if (!netdev->dcbnl_ops->getbcnrp || !netdev->dcbnl_ops->getbcncfg) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(bcn_tb, DCB_BCN_ATTR_MAX, tb[DCB_ATTR_BCN], dcbnl_bcn_nest, NULL); if (ret) return ret; bcn_nest = nla_nest_start_noflag(skb, DCB_ATTR_BCN); if (!bcn_nest) return -EMSGSIZE; if (bcn_tb[DCB_BCN_ATTR_ALL]) getall = true; for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) { if (!getall && !bcn_tb[i]) continue; netdev->dcbnl_ops->getbcnrp(netdev, i - DCB_BCN_ATTR_RP_0, &value_byte); ret = nla_put_u8(skb, i, value_byte); if (ret) goto err_bcn; } for (i = DCB_BCN_ATTR_BCNA_0; i <= DCB_BCN_ATTR_RI; i++) { if (!getall && !bcn_tb[i]) continue; netdev->dcbnl_ops->getbcncfg(netdev, i, &value_integer); ret = nla_put_u32(skb, i, value_integer); if (ret) goto err_bcn; } nla_nest_end(skb, bcn_nest); return 0; err_bcn: nla_nest_cancel(skb, bcn_nest); return ret; } static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_BCN_ATTR_MAX + 1]; int i; int ret; u8 value_byte; u32 value_int; if (!tb[DCB_ATTR_BCN]) return -EINVAL; if (!netdev->dcbnl_ops->setbcncfg || !netdev->dcbnl_ops->setbcnrp) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_BCN_ATTR_MAX, tb[DCB_ATTR_BCN], dcbnl_bcn_nest, NULL); if (ret) return ret; for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) { if (data[i] == NULL) continue; value_byte = nla_get_u8(data[i]); netdev->dcbnl_ops->setbcnrp(netdev, data[i]->nla_type - DCB_BCN_ATTR_RP_0, value_byte); } for (i = DCB_BCN_ATTR_BCNA_0; i <= DCB_BCN_ATTR_RI; i++) { if (data[i] == NULL) continue; value_int = nla_get_u32(data[i]); netdev->dcbnl_ops->setbcncfg(netdev, i, value_int); } return nla_put_u8(skb, DCB_ATTR_BCN, 0); } static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb, int app_nested_type, int app_info_type, int app_entry_type) { struct dcb_peer_app_info info; struct dcb_app *table = NULL; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; u16 app_count; int err; /** * retrieve the peer app configuration form the driver. If the driver * handlers fail exit without doing anything */ err = ops->peer_getappinfo(netdev, &info, &app_count); if (!err && app_count) { table = kmalloc_array(app_count, sizeof(struct dcb_app), GFP_KERNEL); if (!table) return -ENOMEM; err = ops->peer_getapptable(netdev, table); } if (!err) { u16 i; struct nlattr *app; /** * build the message, from here on the only possible failure * is due to the skb size */ err = -EMSGSIZE; app = nla_nest_start_noflag(skb, app_nested_type); if (!app) goto nla_put_failure; if (app_info_type && nla_put(skb, app_info_type, sizeof(info), &info)) goto nla_put_failure; for (i = 0; i < app_count; i++) { if (nla_put(skb, app_entry_type, sizeof(struct dcb_app), &table[i])) goto nla_put_failure; } nla_nest_end(skb, app); } err = 0; nla_put_failure: kfree(table); return err; } static int dcbnl_getapptrust(struct net_device *netdev, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; enum ieee_attrs_app type; struct nlattr *apptrust; int nselectors, err, i; u8 *selectors; selectors = kzalloc(IEEE_8021QAZ_APP_SEL_MAX + 1, GFP_KERNEL); if (!selectors) return -ENOMEM; err = ops->dcbnl_getapptrust(netdev, selectors, &nselectors); if (err) { err = 0; goto out; } apptrust = nla_nest_start(skb, DCB_ATTR_DCB_APP_TRUST_TABLE); if (!apptrust) { err = -EMSGSIZE; goto out; } for (i = 0; i < nselectors; i++) { type = dcbnl_app_attr_type_get(selectors[i]); err = nla_put_u8(skb, type, selectors[i]); if (err) { nla_nest_cancel(skb, apptrust); goto out; } } nla_nest_end(skb, apptrust); out: kfree(selectors); return err; } /* Set or delete APP table or rewrite table entries. The APP struct is validated * and the appropriate callback function is called. */ static int dcbnl_app_table_setdel(struct nlattr *attr, struct net_device *netdev, int (*setdel)(struct net_device *dev, struct dcb_app *app)) { struct dcb_app *app_data; enum ieee_attrs_app type; struct nlattr *attr_itr; int rem, err; nla_for_each_nested(attr_itr, attr, rem) { type = nla_type(attr_itr); if (!dcbnl_app_attr_type_validate(type)) continue; if (nla_len(attr_itr) < sizeof(struct dcb_app)) return -ERANGE; app_data = nla_data(attr_itr); if (!dcbnl_app_selector_validate(type, app_data->selector)) return -EINVAL; err = setdel(netdev, app_data); if (err) return err; } return 0; } /* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb GET commands. */ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee, *app, *rewr; struct dcb_app_type *itr; int dcbx; int err; if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) return -EMSGSIZE; ieee = nla_nest_start_noflag(skb, DCB_ATTR_IEEE); if (!ieee) return -EMSGSIZE; if (ops->ieee_getets) { struct ieee_ets ets; memset(&ets, 0, sizeof(ets)); err = ops->ieee_getets(netdev, &ets); if (!err && nla_put(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets)) return -EMSGSIZE; } if (ops->ieee_getmaxrate) { struct ieee_maxrate maxrate; memset(&maxrate, 0, sizeof(maxrate)); err = ops->ieee_getmaxrate(netdev, &maxrate); if (!err) { err = nla_put(skb, DCB_ATTR_IEEE_MAXRATE, sizeof(maxrate), &maxrate); if (err) return -EMSGSIZE; } } if (ops->ieee_getqcn) { struct ieee_qcn qcn; memset(&qcn, 0, sizeof(qcn)); err = ops->ieee_getqcn(netdev, &qcn); if (!err) { err = nla_put(skb, DCB_ATTR_IEEE_QCN, sizeof(qcn), &qcn); if (err) return -EMSGSIZE; } } if (ops->ieee_getqcnstats) { struct ieee_qcn_stats qcn_stats; memset(&qcn_stats, 0, sizeof(qcn_stats)); err = ops->ieee_getqcnstats(netdev, &qcn_stats); if (!err) { err = nla_put(skb, DCB_ATTR_IEEE_QCN_STATS, sizeof(qcn_stats), &qcn_stats); if (err) return -EMSGSIZE; } } if (ops->ieee_getpfc) { struct ieee_pfc pfc; memset(&pfc, 0, sizeof(pfc)); err = ops->ieee_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc)) return -EMSGSIZE; } if (ops->dcbnl_getbuffer) { struct dcbnl_buffer buffer; memset(&buffer, 0, sizeof(buffer)); err = ops->dcbnl_getbuffer(netdev, &buffer); if (!err && nla_put(skb, DCB_ATTR_DCB_BUFFER, sizeof(buffer), &buffer)) return -EMSGSIZE; } app = nla_nest_start_noflag(skb, DCB_ATTR_IEEE_APP_TABLE); if (!app) return -EMSGSIZE; spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == netdev->ifindex) { enum ieee_attrs_app type = dcbnl_app_attr_type_get(itr->app.selector); err = nla_put(skb, type, sizeof(itr->app), &itr->app); if (err) { spin_unlock_bh(&dcb_lock); return -EMSGSIZE; } } } if (netdev->dcbnl_ops->getdcbx) dcbx = netdev->dcbnl_ops->getdcbx(netdev); else dcbx = -EOPNOTSUPP; spin_unlock_bh(&dcb_lock); nla_nest_end(skb, app); rewr = nla_nest_start(skb, DCB_ATTR_DCB_REWR_TABLE); if (!rewr) return -EMSGSIZE; spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_rewr_list, list) { if (itr->ifindex == netdev->ifindex) { enum ieee_attrs_app type = dcbnl_app_attr_type_get(itr->app.selector); err = nla_put(skb, type, sizeof(itr->app), &itr->app); if (err) { spin_unlock_bh(&dcb_lock); nla_nest_cancel(skb, rewr); return -EMSGSIZE; } } } spin_unlock_bh(&dcb_lock); nla_nest_end(skb, rewr); if (ops->dcbnl_getapptrust) { err = dcbnl_getapptrust(netdev, skb); if (err) return err; } /* get peer info if available */ if (ops->ieee_peer_getets) { struct ieee_ets ets; memset(&ets, 0, sizeof(ets)); err = ops->ieee_peer_getets(netdev, &ets); if (!err && nla_put(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets)) return -EMSGSIZE; } if (ops->ieee_peer_getpfc) { struct ieee_pfc pfc; memset(&pfc, 0, sizeof(pfc)); err = ops->ieee_peer_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc)) return -EMSGSIZE; } if (ops->peer_getappinfo && ops->peer_getapptable) { err = dcbnl_build_peer_app(netdev, skb, DCB_ATTR_IEEE_PEER_APP, DCB_ATTR_IEEE_APP_UNSPEC, DCB_ATTR_IEEE_APP); if (err) return -EMSGSIZE; } nla_nest_end(skb, ieee); if (dcbx >= 0) { err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx); if (err) return -EMSGSIZE; } return 0; } static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, int dir) { u8 pgid, up_map, prio, tc_pct; const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops; int i = dir ? DCB_ATTR_CEE_TX_PG : DCB_ATTR_CEE_RX_PG; struct nlattr *pg = nla_nest_start_noflag(skb, i); if (!pg) return -EMSGSIZE; for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { struct nlattr *tc_nest = nla_nest_start_noflag(skb, i); if (!tc_nest) return -EMSGSIZE; pgid = DCB_ATTR_VALUE_UNDEFINED; prio = DCB_ATTR_VALUE_UNDEFINED; tc_pct = DCB_ATTR_VALUE_UNDEFINED; up_map = DCB_ATTR_VALUE_UNDEFINED; if (!dir) ops->getpgtccfgrx(dev, i - DCB_PG_ATTR_TC_0, &prio, &pgid, &tc_pct, &up_map); else ops->getpgtccfgtx(dev, i - DCB_PG_ATTR_TC_0, &prio, &pgid, &tc_pct, &up_map); if (nla_put_u8(skb, DCB_TC_ATTR_PARAM_PGID, pgid) || nla_put_u8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map) || nla_put_u8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio) || nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct)) return -EMSGSIZE; nla_nest_end(skb, tc_nest); } for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) { tc_pct = DCB_ATTR_VALUE_UNDEFINED; if (!dir) ops->getpgbwgcfgrx(dev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); else ops->getpgbwgcfgtx(dev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); if (nla_put_u8(skb, i, tc_pct)) return -EMSGSIZE; } nla_nest_end(skb, pg); return 0; } static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) { struct nlattr *cee, *app; struct dcb_app_type *itr; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; int dcbx, i, err = -EMSGSIZE; u8 value; if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) goto nla_put_failure; cee = nla_nest_start_noflag(skb, DCB_ATTR_CEE); if (!cee) goto nla_put_failure; /* local pg */ if (ops->getpgtccfgtx && ops->getpgbwgcfgtx) { err = dcbnl_cee_pg_fill(skb, netdev, 1); if (err) goto nla_put_failure; } if (ops->getpgtccfgrx && ops->getpgbwgcfgrx) { err = dcbnl_cee_pg_fill(skb, netdev, 0); if (err) goto nla_put_failure; } /* local pfc */ if (ops->getpfccfg) { struct nlattr *pfc_nest = nla_nest_start_noflag(skb, DCB_ATTR_CEE_PFC); if (!pfc_nest) goto nla_put_failure; for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0, &value); if (nla_put_u8(skb, i, value)) goto nla_put_failure; } nla_nest_end(skb, pfc_nest); } /* local app */ spin_lock_bh(&dcb_lock); app = nla_nest_start_noflag(skb, DCB_ATTR_CEE_APP_TABLE); if (!app) goto dcb_unlock; list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == netdev->ifindex) { struct nlattr *app_nest = nla_nest_start_noflag(skb, DCB_ATTR_APP); if (!app_nest) goto dcb_unlock; err = nla_put_u8(skb, DCB_APP_ATTR_IDTYPE, itr->app.selector); if (err) goto dcb_unlock; err = nla_put_u16(skb, DCB_APP_ATTR_ID, itr->app.protocol); if (err) goto dcb_unlock; err = nla_put_u8(skb, DCB_APP_ATTR_PRIORITY, itr->app.priority); if (err) goto dcb_unlock; nla_nest_end(skb, app_nest); } } nla_nest_end(skb, app); if (netdev->dcbnl_ops->getdcbx) dcbx = netdev->dcbnl_ops->getdcbx(netdev); else dcbx = -EOPNOTSUPP; spin_unlock_bh(&dcb_lock); /* features flags */ if (ops->getfeatcfg) { struct nlattr *feat = nla_nest_start_noflag(skb, DCB_ATTR_CEE_FEAT); if (!feat) goto nla_put_failure; for (i = DCB_FEATCFG_ATTR_ALL + 1; i <= DCB_FEATCFG_ATTR_MAX; i++) if (!ops->getfeatcfg(netdev, i, &value) && nla_put_u8(skb, i, value)) goto nla_put_failure; nla_nest_end(skb, feat); } /* peer info if available */ if (ops->cee_peer_getpg) { struct cee_pg pg; memset(&pg, 0, sizeof(pg)); err = ops->cee_peer_getpg(netdev, &pg); if (!err && nla_put(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg)) goto nla_put_failure; } if (ops->cee_peer_getpfc) { struct cee_pfc pfc; memset(&pfc, 0, sizeof(pfc)); err = ops->cee_peer_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc)) goto nla_put_failure; } if (ops->peer_getappinfo && ops->peer_getapptable) { err = dcbnl_build_peer_app(netdev, skb, DCB_ATTR_CEE_PEER_APP_TABLE, DCB_ATTR_CEE_PEER_APP_INFO, DCB_ATTR_CEE_PEER_APP); if (err) goto nla_put_failure; } nla_nest_end(skb, cee); /* DCBX state */ if (dcbx >= 0) { err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx); if (err) goto nla_put_failure; } return 0; dcb_unlock: spin_unlock_bh(&dcb_lock); nla_put_failure: err = -EMSGSIZE; return err; } static int dcbnl_notify(struct net_device *dev, int event, int cmd, u32 seq, u32 portid, int dcbx_ver) { struct net *net = dev_net(dev); struct sk_buff *skb; struct nlmsghdr *nlh; const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops; int err; if (!ops) return -EOPNOTSUPP; skb = dcbnl_newmsg(event, cmd, portid, seq, 0, &nlh); if (!skb) return -ENOMEM; if (dcbx_ver == DCB_CAP_DCBX_VER_IEEE) err = dcbnl_ieee_fill(skb, dev); else err = dcbnl_cee_fill(skb, dev); if (err < 0) { /* Report error to broadcast listeners */ nlmsg_free(skb); rtnl_set_sk_err(net, RTNLGRP_DCB, err); } else { /* End nlmsg and notify broadcast listeners */ nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_DCB, NULL, GFP_KERNEL); } return err; } int dcbnl_ieee_notify(struct net_device *dev, int event, int cmd, u32 seq, u32 portid) { return dcbnl_notify(dev, event, cmd, seq, portid, DCB_CAP_DCBX_VER_IEEE); } EXPORT_SYMBOL(dcbnl_ieee_notify); int dcbnl_cee_notify(struct net_device *dev, int event, int cmd, u32 seq, u32 portid) { return dcbnl_notify(dev, event, cmd, seq, portid, DCB_CAP_DCBX_VER_CEE); } EXPORT_SYMBOL(dcbnl_cee_notify); /* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb SET commands. * If any requested operation can not be completed * the entire msg is aborted and error value is returned. * No attempt is made to reconcile the case where only part of the * cmd can be completed. */ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; int prio; int err; if (!ops) return -EOPNOTSUPP; if (!tb[DCB_ATTR_IEEE]) return -EINVAL; err = nla_parse_nested_deprecated(ieee, DCB_ATTR_IEEE_MAX, tb[DCB_ATTR_IEEE], dcbnl_ieee_policy, NULL); if (err) return err; if (ieee[DCB_ATTR_IEEE_ETS] && ops->ieee_setets) { struct ieee_ets *ets = nla_data(ieee[DCB_ATTR_IEEE_ETS]); err = ops->ieee_setets(netdev, ets); if (err) goto err; } if (ieee[DCB_ATTR_IEEE_MAXRATE] && ops->ieee_setmaxrate) { struct ieee_maxrate *maxrate = nla_data(ieee[DCB_ATTR_IEEE_MAXRATE]); err = ops->ieee_setmaxrate(netdev, maxrate); if (err) goto err; } if (ieee[DCB_ATTR_IEEE_QCN] && ops->ieee_setqcn) { struct ieee_qcn *qcn = nla_data(ieee[DCB_ATTR_IEEE_QCN]); err = ops->ieee_setqcn(netdev, qcn); if (err) goto err; } if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) { struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]); err = ops->ieee_setpfc(netdev, pfc); if (err) goto err; } if (ieee[DCB_ATTR_DCB_BUFFER] && ops->dcbnl_setbuffer) { struct dcbnl_buffer *buffer = nla_data(ieee[DCB_ATTR_DCB_BUFFER]); for (prio = 0; prio < ARRAY_SIZE(buffer->prio2buffer); prio++) { if (buffer->prio2buffer[prio] >= DCBX_MAX_BUFFERS) { err = -EINVAL; goto err; } } err = ops->dcbnl_setbuffer(netdev, buffer); if (err) goto err; } if (ieee[DCB_ATTR_DCB_REWR_TABLE]) { err = dcbnl_app_table_setdel(ieee[DCB_ATTR_DCB_REWR_TABLE], netdev, ops->dcbnl_setrewr ?: dcb_setrewr); if (err) goto err; } if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { err = dcbnl_app_table_setdel(ieee[DCB_ATTR_IEEE_APP_TABLE], netdev, ops->ieee_setapp ?: dcb_ieee_setapp); if (err) goto err; } if (ieee[DCB_ATTR_DCB_APP_TRUST_TABLE]) { u8 selectors[IEEE_8021QAZ_APP_SEL_MAX + 1] = {0}; struct nlattr *attr; int nselectors = 0; int rem; if (!ops->dcbnl_setapptrust) { err = -EOPNOTSUPP; goto err; } nla_for_each_nested(attr, ieee[DCB_ATTR_DCB_APP_TRUST_TABLE], rem) { enum ieee_attrs_app type = nla_type(attr); u8 selector; int i; if (!dcbnl_app_attr_type_validate(type) || nla_len(attr) != 1 || nselectors >= sizeof(selectors)) { err = -EINVAL; goto err; } selector = nla_get_u8(attr); if (!dcbnl_app_selector_validate(type, selector)) { err = -EINVAL; goto err; } /* Duplicate selector ? */ for (i = 0; i < nselectors; i++) { if (selectors[i] == selector) { err = -EINVAL; goto err; } } selectors[nselectors++] = selector; } err = ops->dcbnl_setapptrust(netdev, selectors, nselectors); if (err) goto err; } err: err = nla_put_u8(skb, DCB_ATTR_IEEE, err); dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_SET, seq, 0); return err; } static int dcbnl_ieee_get(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; if (!ops) return -EOPNOTSUPP; return dcbnl_ieee_fill(skb, netdev); } static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; int err; if (!ops) return -EOPNOTSUPP; if (!tb[DCB_ATTR_IEEE]) return -EINVAL; err = nla_parse_nested_deprecated(ieee, DCB_ATTR_IEEE_MAX, tb[DCB_ATTR_IEEE], dcbnl_ieee_policy, NULL); if (err) return err; if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { err = dcbnl_app_table_setdel(ieee[DCB_ATTR_IEEE_APP_TABLE], netdev, ops->ieee_delapp ?: dcb_ieee_delapp); if (err) goto err; } if (ieee[DCB_ATTR_DCB_REWR_TABLE]) { err = dcbnl_app_table_setdel(ieee[DCB_ATTR_DCB_REWR_TABLE], netdev, ops->dcbnl_delrewr ?: dcb_delrewr); if (err) goto err; } err: err = nla_put_u8(skb, DCB_ATTR_IEEE, err); dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_DEL, seq, 0); return err; } /* DCBX configuration */ static int dcbnl_getdcbx(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { if (!netdev->dcbnl_ops->getdcbx) return -EOPNOTSUPP; return nla_put_u8(skb, DCB_ATTR_DCBX, netdev->dcbnl_ops->getdcbx(netdev)); } static int dcbnl_setdcbx(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { u8 value; if (!netdev->dcbnl_ops->setdcbx) return -EOPNOTSUPP; if (!tb[DCB_ATTR_DCBX]) return -EINVAL; value = nla_get_u8(tb[DCB_ATTR_DCBX]); return nla_put_u8(skb, DCB_ATTR_DCBX, netdev->dcbnl_ops->setdcbx(netdev, value)); } static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1], *nest; u8 value; int ret, i; int getall = 0; if (!netdev->dcbnl_ops->getfeatcfg) return -EOPNOTSUPP; if (!tb[DCB_ATTR_FEATCFG]) return -EINVAL; ret = nla_parse_nested_deprecated(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG], dcbnl_featcfg_nest, NULL); if (ret) return ret; nest = nla_nest_start_noflag(skb, DCB_ATTR_FEATCFG); if (!nest) return -EMSGSIZE; if (data[DCB_FEATCFG_ATTR_ALL]) getall = 1; for (i = DCB_FEATCFG_ATTR_ALL+1; i <= DCB_FEATCFG_ATTR_MAX; i++) { if (!getall && !data[i]) continue; ret = netdev->dcbnl_ops->getfeatcfg(netdev, i, &value); if (!ret) ret = nla_put_u8(skb, i, value); if (ret) { nla_nest_cancel(skb, nest); goto nla_put_failure; } } nla_nest_end(skb, nest); nla_put_failure: return ret; } static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1]; int ret, i; u8 value; if (!netdev->dcbnl_ops->setfeatcfg) return -ENOTSUPP; if (!tb[DCB_ATTR_FEATCFG]) return -EINVAL; ret = nla_parse_nested_deprecated(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG], dcbnl_featcfg_nest, NULL); if (ret) goto err; for (i = DCB_FEATCFG_ATTR_ALL+1; i <= DCB_FEATCFG_ATTR_MAX; i++) { if (data[i] == NULL) continue; value = nla_get_u8(data[i]); ret = netdev->dcbnl_ops->setfeatcfg(netdev, i, value); if (ret) goto err; } err: ret = nla_put_u8(skb, DCB_ATTR_FEATCFG, ret); return ret; } /* Handle CEE DCBX GET commands. */ static int dcbnl_cee_get(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; if (!ops) return -EOPNOTSUPP; return dcbnl_cee_fill(skb, netdev); } struct reply_func { /* reply netlink message type */ int type; /* function to fill message contents */ int (*cb)(struct net_device *, struct nlmsghdr *, u32, struct nlattr **, struct sk_buff *); }; static const struct reply_func reply_funcs[DCB_CMD_MAX+1] = { [DCB_CMD_GSTATE] = { RTM_GETDCB, dcbnl_getstate }, [DCB_CMD_SSTATE] = { RTM_SETDCB, dcbnl_setstate }, [DCB_CMD_PFC_GCFG] = { RTM_GETDCB, dcbnl_getpfccfg }, [DCB_CMD_PFC_SCFG] = { RTM_SETDCB, dcbnl_setpfccfg }, [DCB_CMD_GPERM_HWADDR] = { RTM_GETDCB, dcbnl_getperm_hwaddr }, [DCB_CMD_GCAP] = { RTM_GETDCB, dcbnl_getcap }, [DCB_CMD_GNUMTCS] = { RTM_GETDCB, dcbnl_getnumtcs }, [DCB_CMD_SNUMTCS] = { RTM_SETDCB, dcbnl_setnumtcs }, [DCB_CMD_PFC_GSTATE] = { RTM_GETDCB, dcbnl_getpfcstate }, [DCB_CMD_PFC_SSTATE] = { RTM_SETDCB, dcbnl_setpfcstate }, [DCB_CMD_GAPP] = { RTM_GETDCB, dcbnl_getapp }, [DCB_CMD_SAPP] = { RTM_SETDCB, dcbnl_setapp }, [DCB_CMD_PGTX_GCFG] = { RTM_GETDCB, dcbnl_pgtx_getcfg }, [DCB_CMD_PGTX_SCFG] = { RTM_SETDCB, dcbnl_pgtx_setcfg }, [DCB_CMD_PGRX_GCFG] = { RTM_GETDCB, dcbnl_pgrx_getcfg }, [DCB_CMD_PGRX_SCFG] = { RTM_SETDCB, dcbnl_pgrx_setcfg }, [DCB_CMD_SET_ALL] = { RTM_SETDCB, dcbnl_setall }, [DCB_CMD_BCN_GCFG] = { RTM_GETDCB, dcbnl_bcn_getcfg }, [DCB_CMD_BCN_SCFG] = { RTM_SETDCB, dcbnl_bcn_setcfg }, [DCB_CMD_IEEE_GET] = { RTM_GETDCB, dcbnl_ieee_get }, [DCB_CMD_IEEE_SET] = { RTM_SETDCB, dcbnl_ieee_set }, [DCB_CMD_IEEE_DEL] = { RTM_SETDCB, dcbnl_ieee_del }, [DCB_CMD_GDCBX] = { RTM_GETDCB, dcbnl_getdcbx }, [DCB_CMD_SDCBX] = { RTM_SETDCB, dcbnl_setdcbx }, [DCB_CMD_GFEATCFG] = { RTM_GETDCB, dcbnl_getfeatcfg }, [DCB_CMD_SFEATCFG] = { RTM_SETDCB, dcbnl_setfeatcfg }, [DCB_CMD_CEE_GET] = { RTM_GETDCB, dcbnl_cee_get }, }; static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct net_device *netdev; struct dcbmsg *dcb = nlmsg_data(nlh); struct nlattr *tb[DCB_ATTR_MAX + 1]; u32 portid = NETLINK_CB(skb).portid; int ret = -EINVAL; struct sk_buff *reply_skb; struct nlmsghdr *reply_nlh = NULL; const struct reply_func *fn; if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse_deprecated(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX, dcbnl_rtnl_policy, extack); if (ret < 0) return ret; if (dcb->cmd > DCB_CMD_MAX) return -EINVAL; /* check if a reply function has been defined for the command */ fn = &reply_funcs[dcb->cmd]; if (!fn->cb) return -EOPNOTSUPP; if (fn->type == RTM_SETDCB && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!tb[DCB_ATTR_IFNAME]) return -EINVAL; netdev = __dev_get_by_name(net, nla_data(tb[DCB_ATTR_IFNAME])); if (!netdev) return -ENODEV; if (!netdev->dcbnl_ops) return -EOPNOTSUPP; reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, portid, nlh->nlmsg_seq, nlh->nlmsg_flags, &reply_nlh); if (!reply_skb) return -ENOMEM; ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb); if (ret < 0) { nlmsg_free(reply_skb); goto out; } nlmsg_end(reply_skb, reply_nlh); ret = rtnl_unicast(reply_skb, net, portid); out: return ret; } static struct dcb_app_type *dcb_rewr_lookup(const struct dcb_app *app, int ifindex, int proto) { struct dcb_app_type *itr; list_for_each_entry(itr, &dcb_rewr_list, list) { if (itr->app.selector == app->selector && itr->app.priority == app->priority && itr->ifindex == ifindex && ((proto == -1) || itr->app.protocol == proto)) return itr; } return NULL; } static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app, int ifindex, int prio) { struct dcb_app_type *itr; list_for_each_entry(itr, &dcb_app_list, list) { if (itr->app.selector == app->selector && itr->app.protocol == app->protocol && itr->ifindex == ifindex && ((prio == -1) || itr->app.priority == prio)) return itr; } return NULL; } static int dcb_app_add(struct list_head *list, const struct dcb_app *app, int ifindex) { struct dcb_app_type *entry; entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) return -ENOMEM; memcpy(&entry->app, app, sizeof(*app)); entry->ifindex = ifindex; list_add(&entry->list, list); return 0; } /** * dcb_getapp - retrieve the DCBX application user priority * @dev: network interface * @app: application to get user priority of * * On success returns a non-zero 802.1p user priority bitmap * otherwise returns 0 as the invalid user priority bitmap to * indicate an error. */ u8 dcb_getapp(struct net_device *dev, struct dcb_app *app) { struct dcb_app_type *itr; u8 prio = 0; spin_lock_bh(&dcb_lock); itr = dcb_app_lookup(app, dev->ifindex, -1); if (itr) prio = itr->app.priority; spin_unlock_bh(&dcb_lock); return prio; } EXPORT_SYMBOL(dcb_getapp); /** * dcb_setapp - add CEE dcb application data to app list * @dev: network interface * @new: application data to add * * Priority 0 is an invalid priority in CEE spec. This routine * removes applications from the app list if the priority is * set to zero. Priority is expected to be 8-bit 802.1p user priority bitmap */ int dcb_setapp(struct net_device *dev, struct dcb_app *new) { struct dcb_app_type *itr; struct dcb_app_type event; int err = 0; event.ifindex = dev->ifindex; memcpy(&event.app, new, sizeof(event.app)); if (dev->dcbnl_ops->getdcbx) event.dcbx = dev->dcbnl_ops->getdcbx(dev); spin_lock_bh(&dcb_lock); /* Search for existing match and replace */ itr = dcb_app_lookup(new, dev->ifindex, -1); if (itr) { if (new->priority) itr->app.priority = new->priority; else { list_del(&itr->list); kfree(itr); } goto out; } /* App type does not exist add new application type */ if (new->priority) err = dcb_app_add(&dcb_app_list, new, dev->ifindex); out: spin_unlock_bh(&dcb_lock); if (!err) call_dcbevent_notifiers(DCB_APP_EVENT, &event); return err; } EXPORT_SYMBOL(dcb_setapp); /** * dcb_ieee_getapp_mask - retrieve the IEEE DCB application priority * @dev: network interface * @app: where to store the retrieve application data * * Helper routine which on success returns a non-zero 802.1Qaz user * priority bitmap otherwise returns 0 to indicate the dcb_app was * not found in APP list. */ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app) { struct dcb_app_type *itr; u8 prio = 0; spin_lock_bh(&dcb_lock); itr = dcb_app_lookup(app, dev->ifindex, -1); if (itr) prio |= 1 << itr->app.priority; spin_unlock_bh(&dcb_lock); return prio; } EXPORT_SYMBOL(dcb_ieee_getapp_mask); /* Get protocol value from rewrite entry. */ u16 dcb_getrewr(struct net_device *dev, struct dcb_app *app) { struct dcb_app_type *itr; u16 proto = 0; spin_lock_bh(&dcb_lock); itr = dcb_rewr_lookup(app, dev->ifindex, -1); if (itr) proto = itr->app.protocol; spin_unlock_bh(&dcb_lock); return proto; } EXPORT_SYMBOL(dcb_getrewr); /* Add rewrite entry to the rewrite list. */ int dcb_setrewr(struct net_device *dev, struct dcb_app *new) { int err; spin_lock_bh(&dcb_lock); /* Search for existing match and abort if found. */ if (dcb_rewr_lookup(new, dev->ifindex, new->protocol)) { err = -EEXIST; goto out; } err = dcb_app_add(&dcb_rewr_list, new, dev->ifindex); out: spin_unlock_bh(&dcb_lock); return err; } EXPORT_SYMBOL(dcb_setrewr); /* Delete rewrite entry from the rewrite list. */ int dcb_delrewr(struct net_device *dev, struct dcb_app *del) { struct dcb_app_type *itr; int err = -ENOENT; spin_lock_bh(&dcb_lock); /* Search for existing match and remove it. */ itr = dcb_rewr_lookup(del, dev->ifindex, del->protocol); if (itr) { list_del(&itr->list); kfree(itr); err = 0; } spin_unlock_bh(&dcb_lock); return err; } EXPORT_SYMBOL(dcb_delrewr); /** * dcb_ieee_setapp - add IEEE dcb application data to app list * @dev: network interface * @new: application data to add * * This adds Application data to the list. Multiple application * entries may exists for the same selector and protocol as long * as the priorities are different. Priority is expected to be a * 3-bit unsigned integer */ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) { struct dcb_app_type event; int err = 0; event.ifindex = dev->ifindex; memcpy(&event.app, new, sizeof(event.app)); if (dev->dcbnl_ops->getdcbx) event.dcbx = dev->dcbnl_ops->getdcbx(dev); spin_lock_bh(&dcb_lock); /* Search for existing match and abort if found */ if (dcb_app_lookup(new, dev->ifindex, new->priority)) { err = -EEXIST; goto out; } err = dcb_app_add(&dcb_app_list, new, dev->ifindex); out: spin_unlock_bh(&dcb_lock); if (!err) call_dcbevent_notifiers(DCB_APP_EVENT, &event); return err; } EXPORT_SYMBOL(dcb_ieee_setapp); /** * dcb_ieee_delapp - delete IEEE dcb application data from list * @dev: network interface * @del: application data to delete * * This removes a matching APP data from the APP list */ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) { struct dcb_app_type *itr; struct dcb_app_type event; int err = -ENOENT; event.ifindex = dev->ifindex; memcpy(&event.app, del, sizeof(event.app)); if (dev->dcbnl_ops->getdcbx) event.dcbx = dev->dcbnl_ops->getdcbx(dev); spin_lock_bh(&dcb_lock); /* Search for existing match and remove it. */ if ((itr = dcb_app_lookup(del, dev->ifindex, del->priority))) { list_del(&itr->list); kfree(itr); err = 0; } spin_unlock_bh(&dcb_lock); if (!err) call_dcbevent_notifiers(DCB_APP_EVENT, &event); return err; } EXPORT_SYMBOL(dcb_ieee_delapp); /* dcb_getrewr_prio_pcp_mask_map - For a given device, find mapping from * priorities to the PCP and DEI values assigned to that priority. */ void dcb_getrewr_prio_pcp_mask_map(const struct net_device *dev, struct dcb_rewr_prio_pcp_map *p_map) { int ifindex = dev->ifindex; struct dcb_app_type *itr; u8 prio; memset(p_map->map, 0, sizeof(p_map->map)); spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_rewr_list, list) { if (itr->ifindex == ifindex && itr->app.selector == DCB_APP_SEL_PCP && itr->app.protocol < 16 && itr->app.priority < IEEE_8021QAZ_MAX_TCS) { prio = itr->app.priority; p_map->map[prio] |= 1 << itr->app.protocol; } } spin_unlock_bh(&dcb_lock); } EXPORT_SYMBOL(dcb_getrewr_prio_pcp_mask_map); /* dcb_getrewr_prio_dscp_mask_map - For a given device, find mapping from * priorities to the DSCP values assigned to that priority. */ void dcb_getrewr_prio_dscp_mask_map(const struct net_device *dev, struct dcb_ieee_app_prio_map *p_map) { int ifindex = dev->ifindex; struct dcb_app_type *itr; u8 prio; memset(p_map->map, 0, sizeof(p_map->map)); spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_rewr_list, list) { if (itr->ifindex == ifindex && itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && itr->app.protocol < 64 && itr->app.priority < IEEE_8021QAZ_MAX_TCS) { prio = itr->app.priority; p_map->map[prio] |= 1ULL << itr->app.protocol; } } spin_unlock_bh(&dcb_lock); } EXPORT_SYMBOL(dcb_getrewr_prio_dscp_mask_map); /* * dcb_ieee_getapp_prio_dscp_mask_map - For a given device, find mapping from * priorities to the DSCP values assigned to that priority. Initialize p_map * such that each map element holds a bit mask of DSCP values configured for * that priority by APP entries. */ void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev, struct dcb_ieee_app_prio_map *p_map) { int ifindex = dev->ifindex; struct dcb_app_type *itr; u8 prio; memset(p_map->map, 0, sizeof(p_map->map)); spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == ifindex && itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && itr->app.protocol < 64 && itr->app.priority < IEEE_8021QAZ_MAX_TCS) { prio = itr->app.priority; p_map->map[prio] |= 1ULL << itr->app.protocol; } } spin_unlock_bh(&dcb_lock); } EXPORT_SYMBOL(dcb_ieee_getapp_prio_dscp_mask_map); /* * dcb_ieee_getapp_dscp_prio_mask_map - For a given device, find mapping from * DSCP values to the priorities assigned to that DSCP value. Initialize p_map * such that each map element holds a bit mask of priorities configured for a * given DSCP value by APP entries. */ void dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev, struct dcb_ieee_app_dscp_map *p_map) { int ifindex = dev->ifindex; struct dcb_app_type *itr; memset(p_map->map, 0, sizeof(p_map->map)); spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == ifindex && itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && itr->app.protocol < 64 && itr->app.priority < IEEE_8021QAZ_MAX_TCS) p_map->map[itr->app.protocol] |= 1 << itr->app.priority; } spin_unlock_bh(&dcb_lock); } EXPORT_SYMBOL(dcb_ieee_getapp_dscp_prio_mask_map); /* * Per 802.1Q-2014, the selector value of 1 is used for matching on Ethernet * type, with valid PID values >= 1536. A special meaning is then assigned to * protocol value of 0: "default priority. For use when priority is not * otherwise specified". * * dcb_ieee_getapp_default_prio_mask - For a given device, find all APP entries * of the form {$PRIO, ETHERTYPE, 0} and construct a bit mask of all default * priorities set by these entries. */ u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev) { int ifindex = dev->ifindex; struct dcb_app_type *itr; u8 mask = 0; spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == ifindex && itr->app.selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && itr->app.protocol == 0 && itr->app.priority < IEEE_8021QAZ_MAX_TCS) mask |= 1 << itr->app.priority; } spin_unlock_bh(&dcb_lock); return mask; } EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask); static void dcbnl_flush_dev(struct net_device *dev) { struct dcb_app_type *itr, *tmp; spin_lock_bh(&dcb_lock); list_for_each_entry_safe(itr, tmp, &dcb_app_list, list) { if (itr->ifindex == dev->ifindex) { list_del(&itr->list); kfree(itr); } } spin_unlock_bh(&dcb_lock); } static int dcbnl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_UNREGISTER: if (!dev->dcbnl_ops) return NOTIFY_DONE; dcbnl_flush_dev(dev); return NOTIFY_OK; default: return NOTIFY_DONE; } } static struct notifier_block dcbnl_nb __read_mostly = { .notifier_call = dcbnl_netdevice_event, }; static int __init dcbnl_init(void) { int err; err = register_netdevice_notifier(&dcbnl_nb); if (err) return err; rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, 0); rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, 0); return 0; } device_initcall(dcbnl_init); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Copyright (C) 2007 Alan Stern * Copyright (C) 2009 IBM Corporation * Copyright (C) 2009 Frederic Weisbecker <fweisbec@gmail.com> * * Authors: Alan Stern <stern@rowland.harvard.edu> * K.Prasad <prasad@linux.vnet.ibm.com> * Frederic Weisbecker <fweisbec@gmail.com> */ /* * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility, * using the CPU's debug registers. */ #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> #include <linux/irqflags.h> #include <linux/notifier.h> #include <linux/kallsyms.h> #include <linux/kprobes.h> #include <linux/percpu.h> #include <linux/kdebug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/smp.h> #include <asm/hw_breakpoint.h> #include <asm/processor.h> #include <asm/debugreg.h> #include <asm/user.h> #include <asm/desc.h> #include <asm/tlbflush.h> /* Per cpu debug control register value */ DEFINE_PER_CPU(unsigned long, cpu_dr7); EXPORT_PER_CPU_SYMBOL(cpu_dr7); /* Per cpu debug address registers values */ static DEFINE_PER_CPU(unsigned long, cpu_debugreg[HBP_NUM]); /* * Stores the breakpoints currently in use on each breakpoint address * register for each cpus */ static DEFINE_PER_CPU(struct perf_event *, bp_per_reg[HBP_NUM]); static inline unsigned long __encode_dr7(int drnum, unsigned int len, unsigned int type) { unsigned long bp_info; bp_info = (len | type) & 0xf; bp_info <<= (DR_CONTROL_SHIFT + drnum * DR_CONTROL_SIZE); bp_info |= (DR_GLOBAL_ENABLE << (drnum * DR_ENABLE_SIZE)); return bp_info; } /* * Encode the length, type, Exact, and Enable bits for a particular breakpoint * as stored in debug register 7. */ unsigned long encode_dr7(int drnum, unsigned int len, unsigned int type) { return __encode_dr7(drnum, len, type) | DR_GLOBAL_SLOWDOWN; } /* * Decode the length and type bits for a particular breakpoint as * stored in debug register 7. Return the "enabled" status. */ int decode_dr7(unsigned long dr7, int bpnum, unsigned *len, unsigned *type) { int bp_info = dr7 >> (DR_CONTROL_SHIFT + bpnum * DR_CONTROL_SIZE); *len = (bp_info & 0xc) | 0x40; *type = (bp_info & 0x3) | 0x80; return (dr7 >> (bpnum * DR_ENABLE_SIZE)) & 0x3; } /* * Install a perf counter breakpoint. * * We seek a free debug address register and use it for this * breakpoint. Eventually we enable it in the debug control register. * * Atomic: we hold the counter->ctx->lock and we only handle variables * and registers local to this cpu. */ int arch_install_hw_breakpoint(struct perf_event *bp) { struct arch_hw_breakpoint *info = counter_arch_bp(bp); unsigned long *dr7; int i; lockdep_assert_irqs_disabled(); for (i = 0; i < HBP_NUM; i++) { struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]); if (!*slot) { *slot = bp; break; } } if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot")) return -EBUSY; set_debugreg(info->address, i); __this_cpu_write(cpu_debugreg[i], info->address); dr7 = this_cpu_ptr(&cpu_dr7); *dr7 |= encode_dr7(i, info->len, info->type); /* * Ensure we first write cpu_dr7 before we set the DR7 register. * This ensures an NMI never see cpu_dr7 0 when DR7 is not. */ barrier(); set_debugreg(*dr7, 7); if (info->mask) amd_set_dr_addr_mask(info->mask, i); return 0; } /* * Uninstall the breakpoint contained in the given counter. * * First we search the debug address register it uses and then we disable * it. * * Atomic: we hold the counter->ctx->lock and we only handle variables * and registers local to this cpu. */ void arch_uninstall_hw_breakpoint(struct perf_event *bp) { struct arch_hw_breakpoint *info = counter_arch_bp(bp); unsigned long dr7; int i; lockdep_assert_irqs_disabled(); for (i = 0; i < HBP_NUM; i++) { struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]); if (*slot == bp) { *slot = NULL; break; } } if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot")) return; dr7 = this_cpu_read(cpu_dr7); dr7 &= ~__encode_dr7(i, info->len, info->type); set_debugreg(dr7, 7); if (info->mask) amd_set_dr_addr_mask(0, i); /* * Ensure the write to cpu_dr7 is after we've set the DR7 register. * This ensures an NMI never see cpu_dr7 0 when DR7 is not. */ barrier(); this_cpu_write(cpu_dr7, dr7); } static int arch_bp_generic_len(int x86_len) { switch (x86_len) { case X86_BREAKPOINT_LEN_1: return HW_BREAKPOINT_LEN_1; case X86_BREAKPOINT_LEN_2: return HW_BREAKPOINT_LEN_2; case X86_BREAKPOINT_LEN_4: return HW_BREAKPOINT_LEN_4; #ifdef CONFIG_X86_64 case X86_BREAKPOINT_LEN_8: return HW_BREAKPOINT_LEN_8; #endif default: return -EINVAL; } } int arch_bp_generic_fields(int x86_len, int x86_type, int *gen_len, int *gen_type) { int len; /* Type */ switch (x86_type) { case X86_BREAKPOINT_EXECUTE: if (x86_len != X86_BREAKPOINT_LEN_X) return -EINVAL; *gen_type = HW_BREAKPOINT_X; *gen_len = sizeof(long); return 0; case X86_BREAKPOINT_WRITE: *gen_type = HW_BREAKPOINT_W; break; case X86_BREAKPOINT_RW: *gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R; break; default: return -EINVAL; } /* Len */ len = arch_bp_generic_len(x86_len); if (len < 0) return -EINVAL; *gen_len = len; return 0; } /* * Check for virtual address in kernel space. */ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) { unsigned long va; int len; va = hw->address; len = arch_bp_generic_len(hw->len); WARN_ON_ONCE(len < 0); /* * We don't need to worry about va + len - 1 overflowing: * we already require that va is aligned to a multiple of len. */ return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX); } /* * Checks whether the range [addr, end], overlaps the area [base, base + size). */ static inline bool within_area(unsigned long addr, unsigned long end, unsigned long base, unsigned long size) { return end >= base && addr < (base + size); } /* * Checks whether the range from addr to end, inclusive, overlaps the fixed * mapped CPU entry area range or other ranges used for CPU entry. */ static inline bool within_cpu_entry(unsigned long addr, unsigned long end) { int cpu; /* CPU entry erea is always used for CPU entry */ if (within_area(addr, end, CPU_ENTRY_AREA_BASE, CPU_ENTRY_AREA_MAP_SIZE)) return true; /* * When FSGSBASE is enabled, paranoid_entry() fetches the per-CPU * GSBASE value via __per_cpu_offset or pcpu_unit_offsets. */ #ifdef CONFIG_SMP if (within_area(addr, end, (unsigned long)__per_cpu_offset, sizeof(unsigned long) * nr_cpu_ids)) return true; #else if (within_area(addr, end, (unsigned long)&pcpu_unit_offsets, sizeof(pcpu_unit_offsets))) return true; #endif for_each_possible_cpu(cpu) { /* The original rw GDT is being used after load_direct_gdt() */ if (within_area(addr, end, (unsigned long)get_cpu_gdt_rw(cpu), GDT_SIZE)) return true; /* * cpu_tss_rw is not directly referenced by hardware, but * cpu_tss_rw is also used in CPU entry code, */ if (within_area(addr, end, (unsigned long)&per_cpu(cpu_tss_rw, cpu), sizeof(struct tss_struct))) return true; /* * cpu_tlbstate.user_pcid_flush_mask is used for CPU entry. * If a data breakpoint on it, it will cause an unwanted #DB. * Protect the full cpu_tlbstate structure to be sure. */ if (within_area(addr, end, (unsigned long)&per_cpu(cpu_tlbstate, cpu), sizeof(struct tlb_state))) return true; /* * When in guest (X86_FEATURE_HYPERVISOR), local_db_save() * will read per-cpu cpu_dr7 before clear dr7 register. */ if (within_area(addr, end, (unsigned long)&per_cpu(cpu_dr7, cpu), sizeof(cpu_dr7))) return true; } return false; } static int arch_build_bp_info(struct perf_event *bp, const struct perf_event_attr *attr, struct arch_hw_breakpoint *hw) { unsigned long bp_end; bp_end = attr->bp_addr + attr->bp_len - 1; if (bp_end < attr->bp_addr) return -EINVAL; /* * Prevent any breakpoint of any type that overlaps the CPU * entry area and data. This protects the IST stacks and also * reduces the chance that we ever find out what happens if * there's a data breakpoint on the GDT, IDT, or TSS. */ if (within_cpu_entry(attr->bp_addr, bp_end)) return -EINVAL; hw->address = attr->bp_addr; hw->mask = 0; /* Type */ switch (attr->bp_type) { case HW_BREAKPOINT_W: hw->type = X86_BREAKPOINT_WRITE; break; case HW_BREAKPOINT_W | HW_BREAKPOINT_R: hw->type = X86_BREAKPOINT_RW; break; case HW_BREAKPOINT_X: /* * We don't allow kernel breakpoints in places that are not * acceptable for kprobes. On non-kprobes kernels, we don't * allow kernel breakpoints at all. */ if (attr->bp_addr >= TASK_SIZE_MAX) { if (within_kprobe_blacklist(attr->bp_addr)) return -EINVAL; } hw->type = X86_BREAKPOINT_EXECUTE; /* * x86 inst breakpoints need to have a specific undefined len. * But we still need to check userspace is not trying to setup * an unsupported length, to get a range breakpoint for example. */ if (attr->bp_len == sizeof(long)) { hw->len = X86_BREAKPOINT_LEN_X; return 0; } fallthrough; default: return -EINVAL; } /* Len */ switch (attr->bp_len) { case HW_BREAKPOINT_LEN_1: hw->len = X86_BREAKPOINT_LEN_1; break; case HW_BREAKPOINT_LEN_2: hw->len = X86_BREAKPOINT_LEN_2; break; case HW_BREAKPOINT_LEN_4: hw->len = X86_BREAKPOINT_LEN_4; break; #ifdef CONFIG_X86_64 case HW_BREAKPOINT_LEN_8: hw->len = X86_BREAKPOINT_LEN_8; break; #endif default: /* AMD range breakpoint */ if (!is_power_of_2(attr->bp_len)) return -EINVAL; if (attr->bp_addr & (attr->bp_len - 1)) return -EINVAL; if (!boot_cpu_has(X86_FEATURE_BPEXT)) return -EOPNOTSUPP; /* * It's impossible to use a range breakpoint to fake out * user vs kernel detection because bp_len - 1 can't * have the high bit set. If we ever allow range instruction * breakpoints, then we'll have to check for kprobe-blacklisted * addresses anywhere in the range. */ hw->mask = attr->bp_len - 1; hw->len = X86_BREAKPOINT_LEN_1; } return 0; } /* * Validate the arch-specific HW Breakpoint register settings */ int hw_breakpoint_arch_parse(struct perf_event *bp, const struct perf_event_attr *attr, struct arch_hw_breakpoint *hw) { unsigned int align; int ret; ret = arch_build_bp_info(bp, attr, hw); if (ret) return ret; switch (hw->len) { case X86_BREAKPOINT_LEN_1: align = 0; if (hw->mask) align = hw->mask; break; case X86_BREAKPOINT_LEN_2: align = 1; break; case X86_BREAKPOINT_LEN_4: align = 3; break; #ifdef CONFIG_X86_64 case X86_BREAKPOINT_LEN_8: align = 7; break; #endif default: WARN_ON_ONCE(1); return -EINVAL; } /* * Check that the low-order bits of the address are appropriate * for the alignment implied by len. */ if (hw->address & align) return -EINVAL; return 0; } /* * Release the user breakpoints used by ptrace */ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) { int i; struct thread_struct *t = &tsk->thread; for (i = 0; i < HBP_NUM; i++) { unregister_hw_breakpoint(t->ptrace_bps[i]); t->ptrace_bps[i] = NULL; } t->virtual_dr6 = 0; t->ptrace_dr7 = 0; } void hw_breakpoint_restore(void) { set_debugreg(__this_cpu_read(cpu_debugreg[0]), 0); set_debugreg(__this_cpu_read(cpu_debugreg[1]), 1); set_debugreg(__this_cpu_read(cpu_debugreg[2]), 2); set_debugreg(__this_cpu_read(cpu_debugreg[3]), 3); set_debugreg(DR6_RESERVED, 6); set_debugreg(__this_cpu_read(cpu_dr7), 7); } EXPORT_SYMBOL_GPL(hw_breakpoint_restore); /* * Handle debug exception notifications. * * Return value is either NOTIFY_STOP or NOTIFY_DONE as explained below. * * NOTIFY_DONE returned if one of the following conditions is true. * i) When the causative address is from user-space and the exception * is a valid one, i.e. not triggered as a result of lazy debug register * switching * ii) When there are more bits than trap<n> set in DR6 register (such * as BD, BS or BT) indicating that more than one debug condition is * met and requires some more action in do_debug(). * * NOTIFY_STOP returned for all other cases * */ static int hw_breakpoint_handler(struct die_args *args) { int i, rc = NOTIFY_STOP; struct perf_event *bp; unsigned long *dr6_p; unsigned long dr6; bool bpx; /* The DR6 value is pointed by args->err */ dr6_p = (unsigned long *)ERR_PTR(args->err); dr6 = *dr6_p; /* Do an early return if no trap bits are set in DR6 */ if ((dr6 & DR_TRAP_BITS) == 0) return NOTIFY_DONE; /* Handle all the breakpoints that were triggered */ for (i = 0; i < HBP_NUM; ++i) { if (likely(!(dr6 & (DR_TRAP0 << i)))) continue; bp = this_cpu_read(bp_per_reg[i]); if (!bp) continue; bpx = bp->hw.info.type == X86_BREAKPOINT_EXECUTE; /* * TF and data breakpoints are traps and can be merged, however * instruction breakpoints are faults and will be raised * separately. * * However DR6 can indicate both TF and instruction * breakpoints. In that case take TF as that has precedence and * delay the instruction breakpoint for the next exception. */ if (bpx && (dr6 & DR_STEP)) continue; /* * Reset the 'i'th TRAP bit in dr6 to denote completion of * exception handling */ (*dr6_p) &= ~(DR_TRAP0 << i); perf_bp_event(bp, args->regs); /* * Set up resume flag to avoid breakpoint recursion when * returning back to origin. */ if (bpx) args->regs->flags |= X86_EFLAGS_RF; } /* * Further processing in do_debug() is needed for a) user-space * breakpoints (to generate signals) and b) when the system has * taken exception due to multiple causes */ if ((current->thread.virtual_dr6 & DR_TRAP_BITS) || (dr6 & (~DR_TRAP_BITS))) rc = NOTIFY_DONE; return rc; } /* * Handle debug exception notifications. */ int hw_breakpoint_exceptions_notify( struct notifier_block *unused, unsigned long val, void *data) { if (val != DIE_DEBUG) return NOTIFY_DONE; return hw_breakpoint_handler(data); } void hw_breakpoint_pmu_read(struct perf_event *bp) { /* TODO */ } |
| 6 2319 2319 1367 2196 2240 853 23 23 23 20 2242 1414 2241 142 517 1154 1415 2244 1414 2317 2316 2314 2242 2241 58 2138 2136 67 2118 745 534 954 1842 1156 1 603 145 1005 1263 953 1004 1197 23 17 9 23 2164 1670 2085 2168 2240 2212 2243 1402 1418 2166 89 61 2244 73 77 83 142 2240 58 2241 61 2240 14 309 113 105 311 311 7 311 3 9 311 196 2242 2239 2190 196 2241 1197 666 2243 2243 2244 2244 2234 1197 1601 2143 311 311 310 311 311 310 311 2245 5 2243 2241 5 5 5 5 311 11 11 11 11 2243 2244 2241 2245 196 2188 2240 2245 2241 2245 2243 197 2190 2244 6 2245 2245 310 4 311 311 309 311 653 1202 664 665 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo <tj@kernel.org> * * Copyright (C) 2017 Facebook Inc. * Copyright (C) 2017 Dennis Zhou <dennis@kernel.org> * * The percpu allocator handles both static and dynamic areas. Percpu * areas are allocated in chunks which are divided into units. There is * a 1-to-1 mapping for units to possible cpus. These units are grouped * based on NUMA properties of the machine. * * c0 c1 c2 * ------------------- ------------------- ------------ * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u * ------------------- ...... ------------------- .... ------------ * * Allocation is done by offsets into a unit's address space. Ie., an * area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0, * c1:u1, c1:u2, etc. On NUMA machines, the mapping may be non-linear * and even sparse. Access is handled by configuring percpu base * registers according to the cpu to unit mappings and offsetting the * base address using pcpu_unit_size. * * There is special consideration for the first chunk which must handle * the static percpu variables in the kernel image as allocation services * are not online yet. In short, the first chunk is structured like so: * * <Static | [Reserved] | Dynamic> * * The static data is copied from the original section managed by the * linker. The reserved section, if non-zero, primarily manages static * percpu variables from kernel modules. Finally, the dynamic section * takes care of normal allocations. * * The allocator organizes chunks into lists according to free size and * memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT * flag should be passed. All memcg-aware allocations are sharing one set * of chunks and all unaccounted allocations and allocations performed * by processes belonging to the root memory cgroup are using the second set. * * The allocator tries to allocate from the fullest chunk first. Each chunk * is managed by a bitmap with metadata blocks. The allocation map is updated * on every allocation and free to reflect the current state while the boundary * map is only updated on allocation. Each metadata block contains * information to help mitigate the need to iterate over large portions * of the bitmap. The reverse mapping from page to chunk is stored in * the page's index. Lastly, units are lazily backed and grow in unison. * * There is a unique conversion that goes on here between bytes and bits. * Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE. The chunk * tracks the number of pages it is responsible for in nr_pages. Helper * functions are used to convert from between the bytes, bits, and blocks. * All hints are managed in bits unless explicitly stated. * * To use this allocator, arch code should do the following: * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be * different from the default * * - use pcpu_setup_first_chunk() during percpu area initialization to * setup the first chunk containing the kernel static percpu area */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/bitmap.h> #include <linux/cpumask.h> #include <linux/memblock.h> #include <linux/err.h> #include <linux/list.h> #include <linux/log2.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/pfn.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/memcontrol.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/io.h> #define CREATE_TRACE_POINTS #include <trace/events/percpu.h> #include "percpu-internal.h" /* * The slots are sorted by the size of the biggest continuous free area. * 1-31 bytes share the same slot. */ #define PCPU_SLOT_BASE_SHIFT 5 /* chunks in slots below this are subject to being sidelined on failed alloc */ #define PCPU_SLOT_FAIL_THRESHOLD 3 #define PCPU_EMPTY_POP_PAGES_LOW 2 #define PCPU_EMPTY_POP_PAGES_HIGH 4 #ifdef CONFIG_SMP /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ #ifndef __addr_to_pcpu_ptr #define __addr_to_pcpu_ptr(addr) \ (void __percpu *)((unsigned long)(addr) - \ (unsigned long)pcpu_base_addr + \ (unsigned long)__per_cpu_start) #endif #ifndef __pcpu_ptr_to_addr #define __pcpu_ptr_to_addr(ptr) \ (void __force *)((unsigned long)(ptr) + \ (unsigned long)pcpu_base_addr - \ (unsigned long)__per_cpu_start) #endif #else /* CONFIG_SMP */ /* on UP, it's always identity mapped */ #define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr) #define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr) #endif /* CONFIG_SMP */ static int pcpu_unit_pages __ro_after_init; static int pcpu_unit_size __ro_after_init; static int pcpu_nr_units __ro_after_init; static int pcpu_atom_size __ro_after_init; int pcpu_nr_slots __ro_after_init; static int pcpu_free_slot __ro_after_init; int pcpu_sidelined_slot __ro_after_init; int pcpu_to_depopulate_slot __ro_after_init; static size_t pcpu_chunk_struct_size __ro_after_init; /* cpus with the lowest and highest unit addresses */ static unsigned int pcpu_low_unit_cpu __ro_after_init; static unsigned int pcpu_high_unit_cpu __ro_after_init; /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __ro_after_init; static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */ const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */ /* group information, used for vm allocation */ static int pcpu_nr_groups __ro_after_init; static const unsigned long *pcpu_group_offsets __ro_after_init; static const size_t *pcpu_group_sizes __ro_after_init; /* * The first chunk which always exists. Note that unlike other * chunks, this one can be allocated and mapped in several different * ways and thus often doesn't live in the vmalloc area. */ struct pcpu_chunk *pcpu_first_chunk __ro_after_init; /* * Optional reserved chunk. This chunk reserves part of the first * chunk and serves it for reserved allocations. When the reserved * region doesn't exist, the following variable is NULL. */ struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init; DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ /* * The number of empty populated pages, protected by pcpu_lock. * The reserved chunk doesn't contribute to the count. */ int pcpu_nr_empty_pop_pages; /* * The number of populated pages in use by the allocator, protected by * pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets * allocated/deallocated, it is allocated/deallocated in all units of a chunk * and increments/decrements this count by 1). */ static unsigned long pcpu_nr_populated; /* * Balance work is used to populate or destroy chunks asynchronously. We * try to keep the number of populated free pages between * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one * empty chunk. */ static void pcpu_balance_workfn(struct work_struct *work); static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn); static bool pcpu_async_enabled __read_mostly; static bool pcpu_atomic_alloc_failed; static void pcpu_schedule_balance_work(void) { if (pcpu_async_enabled) schedule_work(&pcpu_balance_work); } /** * pcpu_addr_in_chunk - check if the address is served from this chunk * @chunk: chunk of interest * @addr: percpu address * * RETURNS: * True if the address is served from this chunk. */ static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr) { void *start_addr, *end_addr; if (!chunk) return false; start_addr = chunk->base_addr + chunk->start_offset; end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE - chunk->end_offset; return addr >= start_addr && addr < end_addr; } static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); } static int pcpu_size_to_slot(int size) { if (size == pcpu_unit_size) return pcpu_free_slot; return __pcpu_size_to_slot(size); } static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) { const struct pcpu_block_md *chunk_md = &chunk->chunk_md; if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || chunk_md->contig_hint == 0) return 0; return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE); } /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { page->index = (unsigned long)pcpu; } /* obtain pointer to a chunk from a page struct */ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { return (struct pcpu_chunk *)page->index; } static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx) { return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); } static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { return (unsigned long)chunk->base_addr + pcpu_unit_page_offset(cpu, page_idx); } /* * The following are helper functions to help access bitmaps and convert * between bitmap offsets to address offsets. */ static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index) { return chunk->alloc_map + (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG); } static unsigned long pcpu_off_to_block_index(int off) { return off / PCPU_BITMAP_BLOCK_BITS; } static unsigned long pcpu_off_to_block_off(int off) { return off & (PCPU_BITMAP_BLOCK_BITS - 1); } static unsigned long pcpu_block_off_to_off(int index, int off) { return index * PCPU_BITMAP_BLOCK_BITS + off; } /** * pcpu_check_block_hint - check against the contig hint * @block: block of interest * @bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * * Check to see if the allocation can fit in the block's contig hint. * Note, a chunk uses the same hints as a block so this can also check against * the chunk's contig hint. */ static bool pcpu_check_block_hint(struct pcpu_block_md *block, int bits, size_t align) { int bit_off = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; return bit_off + bits <= block->contig_hint; } /* * pcpu_next_hint - determine which hint to use * @block: block of interest * @alloc_bits: size of allocation * * This determines if we should scan based on the scan_hint or first_free. * In general, we want to scan from first_free to fulfill allocations by * first fit. However, if we know a scan_hint at position scan_hint_start * cannot fulfill an allocation, we can begin scanning from there knowing * the contig_hint will be our fallback. */ static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits) { /* * The three conditions below determine if we can skip past the * scan_hint. First, does the scan hint exist. Second, is the * contig_hint after the scan_hint (possibly not true iff * contig_hint == scan_hint). Third, is the allocation request * larger than the scan_hint. */ if (block->scan_hint && block->contig_hint_start > block->scan_hint_start && alloc_bits > block->scan_hint) return block->scan_hint_start + block->scan_hint; return block->first_free; } /** * pcpu_next_md_free_region - finds the next hint free area * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Helper function for pcpu_for_each_md_free_region. It checks * block->contig_hint and performs aggregation across blocks to find the * next hint. It modifies bit_off and bits in-place to be consumed in the * loop. */ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; return; } /* * This checks three things. First is there a contig_hint to * check. Second, have we checked this hint before by * comparing the block_off. Third, is this the same as the * right contig hint. In the last case, it spills over into * the next block and should be handled by the contig area * across blocks code. */ *bits = block->contig_hint; if (*bits && block->contig_hint_start >= block_off && *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) { *bit_off = pcpu_block_off_to_off(i, block->contig_hint_start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; } } /** * pcpu_next_fit_region - finds fit areas for a given allocation request * @chunk: chunk of interest * @alloc_bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * @bit_off: chunk offset * @bits: size of free area * * Finds the next free region that is viable for use with a given size and * alignment. This only returns if there is a valid area to be used for this * allocation. block->first_free is returned if the allocation request fits * within the block to see if the request can be fulfilled prior to the contig * hint. */ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, int align, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (*bits >= alloc_bits) return; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; } /* check block->contig_hint */ *bits = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; /* * This uses the block offset to determine if this has been * checked in the prior iteration. */ if (block->contig_hint && block->contig_hint_start >= block_off && block->contig_hint >= *bits + alloc_bits) { int start = pcpu_next_hint(block, alloc_bits); *bits += alloc_bits + block->contig_hint_start - start; *bit_off = pcpu_block_off_to_off(i, start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); *bits = PCPU_BITMAP_BLOCK_BITS - *bit_off; *bit_off = pcpu_block_off_to_off(i, *bit_off); if (*bits >= alloc_bits) return; } /* no valid offsets were found - fail condition */ *bit_off = pcpu_chunk_map_bits(chunk); } /* * Metadata free area iterators. These perform aggregation of free areas * based on the metadata blocks and return the offset @bit_off and size in * bits of the free area @bits. pcpu_for_each_fit_region only returns when * a fit is found for the allocation request. */ #define pcpu_for_each_md_free_region(chunk, bit_off, bits) \ for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits) + 1, \ pcpu_next_md_free_region((chunk), &(bit_off), &(bits))) #define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \ for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits), \ pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits))) /** * pcpu_mem_zalloc - allocate memory * @size: bytes to allocate * @gfp: allocation flags * * Allocate @size bytes. If @size is smaller than PAGE_SIZE, * kzalloc() is used; otherwise, the equivalent of vzalloc() is used. * This is to facilitate passing through whitelisted flags. The * returned memory is always zeroed. * * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) { if (WARN_ON_ONCE(!slab_is_available())) return NULL; if (size <= PAGE_SIZE) return kzalloc(size, gfp); else return __vmalloc(size, gfp | __GFP_ZERO); } /** * pcpu_mem_free - free memory * @ptr: memory to free * * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). */ static void pcpu_mem_free(void *ptr) { kvfree(ptr); } static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, bool move_front) { if (chunk != pcpu_reserved_chunk) { if (move_front) list_move(&chunk->list, &pcpu_chunk_lists[slot]); else list_move_tail(&chunk->list, &pcpu_chunk_lists[slot]); } } static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot) { __pcpu_chunk_move(chunk, slot, true); } /** * pcpu_chunk_relocate - put chunk in the appropriate chunk slot * @chunk: chunk of interest * @oslot: the previous slot it was on * * This function is called after an allocation or free changed @chunk. * New slot according to the changed state is determined and @chunk is * moved to the slot. Note that the reserved chunk is never put on * chunk slots. * * CONTEXT: * pcpu_lock. */ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { int nslot = pcpu_chunk_slot(chunk); /* leave isolated chunks in-place */ if (chunk->isolated) return; if (oslot != nslot) __pcpu_chunk_move(chunk, nslot, oslot < nslot); } static void pcpu_isolate_chunk(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); if (!chunk->isolated) { chunk->isolated = true; pcpu_nr_empty_pop_pages -= chunk->nr_empty_pop_pages; } list_move(&chunk->list, &pcpu_chunk_lists[pcpu_to_depopulate_slot]); } static void pcpu_reintegrate_chunk(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); if (chunk->isolated) { chunk->isolated = false; pcpu_nr_empty_pop_pages += chunk->nr_empty_pop_pages; pcpu_chunk_relocate(chunk, -1); } } /* * pcpu_update_empty_pages - update empty page counters * @chunk: chunk of interest * @nr: nr of empty pages * * This is used to keep track of the empty pages now based on the premise * a md_block covers a page. The hint update functions recognize if a block * is made full or broken to calculate deltas for keeping track of free pages. */ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; if (chunk != pcpu_reserved_chunk && !chunk->isolated) pcpu_nr_empty_pop_pages += nr; } /* * pcpu_region_overlap - determines if two regions overlap * @a: start of first region, inclusive * @b: end of first region, exclusive * @x: start of second region, inclusive * @y: end of second region, exclusive * * This is used to determine if the hint region [a, b) overlaps with the * allocated region [x, y). */ static inline bool pcpu_region_overlap(int a, int b, int x, int y) { return (a < y) && (x < b); } /** * pcpu_block_update - updates a block given a free area * @block: block of interest * @start: start offset in block * @end: end offset in block * * Updates a block given a known free area. The region [start, end) is * expected to be the entirety of the free area within a block. Chooses * the best starting offset if the contig hints are equal. */ static void pcpu_block_update(struct pcpu_block_md *block, int start, int end) { int contig = end - start; block->first_free = min(block->first_free, start); if (start == 0) block->left_free = contig; if (end == block->nr_bits) block->right_free = contig; if (contig > block->contig_hint) { /* promote the old contig_hint to be the new scan_hint */ if (start > block->contig_hint_start) { if (block->contig_hint > block->scan_hint) { block->scan_hint_start = block->contig_hint_start; block->scan_hint = block->contig_hint; } else if (start < block->scan_hint_start) { /* * The old contig_hint == scan_hint. But, the * new contig is larger so hold the invariant * scan_hint_start < contig_hint_start. */ block->scan_hint = 0; } } else { block->scan_hint = 0; } block->contig_hint_start = start; block->contig_hint = contig; } else if (contig == block->contig_hint) { if (block->contig_hint_start && (!start || __ffs(start) > __ffs(block->contig_hint_start))) { /* start has a better alignment so use it */ block->contig_hint_start = start; if (start < block->scan_hint_start && block->contig_hint > block->scan_hint) block->scan_hint = 0; } else if (start > block->scan_hint_start || block->contig_hint > block->scan_hint) { /* * Knowing contig == contig_hint, update the scan_hint * if it is farther than or larger than the current * scan_hint. */ block->scan_hint_start = start; block->scan_hint = contig; } } else { /* * The region is smaller than the contig_hint. So only update * the scan_hint if it is larger than or equal and farther than * the current scan_hint. */ if ((start < block->contig_hint_start && (contig > block->scan_hint || (contig == block->scan_hint && start > block->scan_hint_start)))) { block->scan_hint_start = start; block->scan_hint = contig; } } } /* * pcpu_block_update_scan - update a block given a free area from a scan * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Finding the final allocation spot first goes through pcpu_find_block_fit() * to find a block that can hold the allocation and then pcpu_alloc_area() * where a scan is used. When allocations require specific alignments, * we can inadvertently create holes which will not be seen in the alloc * or free paths. * * This takes a given free area hole and updates a block as it may change the * scan_hint. We need to scan backwards to ensure we don't miss free bits * from alignment. */ static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off, int bits) { int s_off = pcpu_off_to_block_off(bit_off); int e_off = s_off + bits; int s_index, l_bit; struct pcpu_block_md *block; if (e_off > PCPU_BITMAP_BLOCK_BITS) return; s_index = pcpu_off_to_block_index(bit_off); block = chunk->md_blocks + s_index; /* scan backwards in case of alignment skipping free bits */ l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), s_off); s_off = (s_off == l_bit) ? 0 : l_bit + 1; pcpu_block_update(block, s_off, e_off); } /** * pcpu_chunk_refresh_hint - updates metadata about a chunk * @chunk: chunk of interest * @full_scan: if we should scan from the beginning * * Iterates over the metadata blocks to find the largest contig area. * A full scan can be avoided on the allocation path as this is triggered * if we broke the contig_hint. In doing so, the scan_hint will be before * the contig_hint or after if the scan_hint == contig_hint. This cannot * be prevented on freeing as we want to find the largest area possibly * spanning blocks. */ static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits; /* promote scan_hint to contig_hint */ if (!full_scan && chunk_md->scan_hint) { bit_off = chunk_md->scan_hint_start + chunk_md->scan_hint; chunk_md->contig_hint_start = chunk_md->scan_hint_start; chunk_md->contig_hint = chunk_md->scan_hint; chunk_md->scan_hint = 0; } else { bit_off = chunk_md->first_free; chunk_md->contig_hint = 0; } bits = 0; pcpu_for_each_md_free_region(chunk, bit_off, bits) pcpu_block_update(chunk_md, bit_off, bit_off + bits); } /** * pcpu_block_refresh_hint * @chunk: chunk of interest * @index: index of the metadata block * * Scans over the block beginning at first_free and updates the block * metadata accordingly. */ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) { struct pcpu_block_md *block = chunk->md_blocks + index; unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index); unsigned int start, end; /* region start, region end */ /* promote scan_hint to contig_hint */ if (block->scan_hint) { start = block->scan_hint_start + block->scan_hint; block->contig_hint_start = block->scan_hint_start; block->contig_hint = block->scan_hint; block->scan_hint = 0; } else { start = block->first_free; block->contig_hint = 0; } block->right_free = 0; /* iterate over free areas and update the contig hints */ for_each_clear_bitrange_from(start, end, alloc_map, PCPU_BITMAP_BLOCK_BITS) pcpu_block_update(block, start, end); } /** * pcpu_block_update_hint_alloc - update hint on allocation path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. The metadata only has to be * refreshed by a full scan iff the chunk's contig hint is broken. Block level * scans are required if the block's contig hint is broken. */ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off, int bits) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Update s_block. */ if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * block->first_free must be updated if the allocation takes its place. * If the allocation breaks the contig_hint, a scan is required to * restore this hint. */ if (s_off == s_block->first_free) s_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, s_index), PCPU_BITMAP_BLOCK_BITS, s_off + bits); if (pcpu_region_overlap(s_block->scan_hint_start, s_block->scan_hint_start + s_block->scan_hint, s_off, s_off + bits)) s_block->scan_hint = 0; if (pcpu_region_overlap(s_block->contig_hint_start, s_block->contig_hint_start + s_block->contig_hint, s_off, s_off + bits)) { /* block contig hint is broken - scan to fix it */ if (!s_off) s_block->left_free = 0; pcpu_block_refresh_hint(chunk, s_index); } else { /* update left and right contig manually */ s_block->left_free = min(s_block->left_free, s_off); if (s_index == e_index) s_block->right_free = min_t(int, s_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); else s_block->right_free = 0; } /* * Update e_block. */ if (s_index != e_index) { if (e_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * When the allocation is across blocks, the end is along * the left part of the e_block. */ e_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, e_off); if (e_off == PCPU_BITMAP_BLOCK_BITS) { /* reset the block */ e_block++; } else { if (e_off > e_block->scan_hint_start) e_block->scan_hint = 0; e_block->left_free = 0; if (e_off > e_block->contig_hint_start) { /* contig hint is broken - scan to fix it */ pcpu_block_refresh_hint(chunk, e_index); } else { e_block->right_free = min_t(int, e_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); } } /* update in-between md_blocks */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->scan_hint = 0; block->contig_hint = 0; block->left_free = 0; block->right_free = 0; } } /* * If the allocation is not atomic, some blocks may not be * populated with pages, while we account it here. The number * of pages will be added back with pcpu_chunk_populated() * when populating pages. */ if (nr_empty_pages) pcpu_update_empty_pages(chunk, -nr_empty_pages); if (pcpu_region_overlap(chunk_md->scan_hint_start, chunk_md->scan_hint_start + chunk_md->scan_hint, bit_off, bit_off + bits)) chunk_md->scan_hint = 0; /* * The only time a full chunk scan is required is if the chunk * contig hint is broken. Otherwise, it means a smaller space * was used and therefore the chunk contig hint is still correct. */ if (pcpu_region_overlap(chunk_md->contig_hint_start, chunk_md->contig_hint_start + chunk_md->contig_hint, bit_off, bit_off + bits)) pcpu_chunk_refresh_hint(chunk, false); } /** * pcpu_block_update_hint_free - updates the block hints on the free path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. This avoids a blind block * refresh by making use of the block contig hints. If this fails, it scans * forward and backward to determine the extent of the free area. This is * capped at the boundary of blocks. * * A chunk update is triggered if a page becomes free, a block becomes free, * or the free spans across blocks. This tradeoff is to minimize iterating * over the block metadata to update chunk_md->contig_hint. * chunk_md->contig_hint may be off by up to a page, but it will never be more * than the available space. If the contig hint is contained in one block, it * will be accurate. */ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, int bits) { int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ int start, end; /* start and end of the whole free area */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Check if the freed area aligns with the block->contig_hint. * If it does, then the scan to find the beginning/end of the * larger free area can be avoided. * * start and end refer to beginning and end of the free area * within each their respective blocks. This is not necessarily * the entire free area as it may span blocks past the beginning * or end of the block. */ start = s_off; if (s_off == s_block->contig_hint + s_block->contig_hint_start) { start = s_block->contig_hint_start; } else { /* * Scan backwards to find the extent of the free area. * find_last_bit returns the starting bit, so if the start bit * is returned, that means there was no last bit and the * remainder of the chunk is free. */ int l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), start); start = (start == l_bit) ? 0 : l_bit + 1; } end = e_off; if (e_off == e_block->contig_hint_start) end = e_block->contig_hint_start + e_block->contig_hint; else end = find_next_bit(pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, end); /* update s_block */ e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS; if (!start && e_off == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(s_block, start, e_off); /* freeing in the same block */ if (s_index != e_index) { /* update e_block */ if (end == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(e_block, 0, end); /* reset md_blocks in the middle */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->first_free = 0; block->scan_hint = 0; block->contig_hint_start = 0; block->contig_hint = PCPU_BITMAP_BLOCK_BITS; block->left_free = PCPU_BITMAP_BLOCK_BITS; block->right_free = PCPU_BITMAP_BLOCK_BITS; } } if (nr_empty_pages) pcpu_update_empty_pages(chunk, nr_empty_pages); /* * Refresh chunk metadata when the free makes a block free or spans * across blocks. The contig_hint may be off by up to a page, but if * the contig_hint is contained in a block, it will be accurate with * the else condition below. */ if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index) pcpu_chunk_refresh_hint(chunk, true); else pcpu_block_update(&chunk->chunk_md, pcpu_block_off_to_off(s_index, start), end); } /** * pcpu_is_populated - determines if the region is populated * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of area * @next_off: return value for the next offset to start searching * * For atomic allocations, check if the backing pages are populated. * * RETURNS: * Bool if the backing pages are populated. * next_index is to skip over unpopulated blocks in pcpu_find_block_fit. */ static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits, int *next_off) { unsigned int start, end; start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE); end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE); start = find_next_zero_bit(chunk->populated, end, start); if (start >= end) return true; end = find_next_bit(chunk->populated, end, start + 1); *next_off = end * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; return false; } /** * pcpu_find_block_fit - finds the block index to start searching * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE bytes) * @pop_only: use populated regions only * * Given a chunk and an allocation spec, find the offset to begin searching * for a free region. This iterates over the bitmap metadata blocks to * find an offset that will be guaranteed to fit the requirements. It is * not quite first fit as if the allocation does not fit in the contig hint * of a block or chunk, it is skipped. This errs on the side of caution * to prevent excess iteration. Poor alignment can cause the allocator to * skip over blocks and chunks that have valid free areas. * * RETURNS: * The offset in the bitmap to begin searching. * -1 if no offset is found. */ static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits, size_t align, bool pop_only) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, next_off; /* * This is an optimization to prevent scanning by assuming if the * allocation cannot fit in the global hint, there is memory pressure * and creating a new chunk would happen soon. */ if (!pcpu_check_block_hint(chunk_md, alloc_bits, align)) return -1; bit_off = pcpu_next_hint(chunk_md, alloc_bits); bits = 0; pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) { if (!pop_only || pcpu_is_populated(chunk, bit_off, bits, &next_off)) break; bit_off = next_off; bits = 0; } if (bit_off == pcpu_chunk_map_bits(chunk)) return -1; return bit_off; } /* * pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off() * @map: the address to base the search on * @size: the bitmap size in bits * @start: the bitnumber to start searching at * @nr: the number of zeroed bits we're looking for * @align_mask: alignment mask for zero area * @largest_off: offset of the largest area skipped * @largest_bits: size of the largest area skipped * * The @align_mask should be one less than a power of 2. * * This is a modified version of bitmap_find_next_zero_area_off() to remember * the largest area that was skipped. This is imperfect, but in general is * good enough. The largest remembered region is the largest failed region * seen. This does not include anything we possibly skipped due to alignment. * pcpu_block_update_scan() does scan backwards to try and recover what was * lost to alignment. While this can cause scanning to miss earlier possible * free areas, smaller allocations will eventually fill those holes. */ static unsigned long pcpu_find_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned long nr, unsigned long align_mask, unsigned long *largest_off, unsigned long *largest_bits) { unsigned long index, end, i, area_off, area_bits; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index, align_mask); area_off = index; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { area_bits = i - area_off; /* remember largest unused area with best alignment */ if (area_bits > *largest_bits || (area_bits == *largest_bits && *largest_off && (!area_off || __ffs(area_off) > __ffs(*largest_off)))) { *largest_off = area_off; *largest_bits = area_bits; } start = i + 1; goto again; } return index; } /** * pcpu_alloc_area - allocates an area from a pcpu_chunk * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE) * @start: bit_off to start searching * * This function takes in a @start offset to begin searching to fit an * allocation of @alloc_bits with alignment @align. It needs to scan * the allocation map because if it fits within the block's contig hint, * @start will be block->first_free. This is an attempt to fill the * allocation prior to breaking the contig hint. The allocation and * boundary maps are updated accordingly if it confirms a valid * free area. * * RETURNS: * Allocated addr offset in @chunk on success. * -1 if no matching area is found. */ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits, size_t align, int start) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; size_t align_mask = (align) ? (align - 1) : 0; unsigned long area_off = 0, area_bits = 0; int bit_off, end, oslot; lockdep_assert_held(&pcpu_lock); oslot = pcpu_chunk_slot(chunk); /* * Search to find a fit. */ end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS, pcpu_chunk_map_bits(chunk)); bit_off = pcpu_find_zero_area(chunk->alloc_map, end, start, alloc_bits, align_mask, &area_off, &area_bits); if (bit_off >= end) return -1; if (area_bits) pcpu_block_update_scan(chunk, area_off, area_bits); /* update alloc map */ bitmap_set(chunk->alloc_map, bit_off, alloc_bits); /* update boundary map */ set_bit(bit_off, chunk->bound_map); bitmap_clear(chunk->bound_map, bit_off + 1, alloc_bits - 1); set_bit(bit_off + alloc_bits, chunk->bound_map); chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE; /* update first free bit */ if (bit_off == chunk_md->first_free) chunk_md->first_free = find_next_zero_bit( chunk->alloc_map, pcpu_chunk_map_bits(chunk), bit_off + alloc_bits); pcpu_block_update_hint_alloc(chunk, bit_off, alloc_bits); pcpu_chunk_relocate(chunk, oslot); return bit_off * PCPU_MIN_ALLOC_SIZE; } /** * pcpu_free_area - frees the corresponding offset * @chunk: chunk of interest * @off: addr offset into chunk * * This function determines the size of an allocation to free using * the boundary bitmap and clears the allocation map. * * RETURNS: * Number of freed bytes. */ static int pcpu_free_area(struct pcpu_chunk *chunk, int off) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, end, oslot, freed; lockdep_assert_held(&pcpu_lock); pcpu_stats_area_dealloc(chunk); oslot = pcpu_chunk_slot(chunk); bit_off = off / PCPU_MIN_ALLOC_SIZE; /* find end index */ end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), bit_off + 1); bits = end - bit_off; bitmap_clear(chunk->alloc_map, bit_off, bits); freed = bits * PCPU_MIN_ALLOC_SIZE; /* update metadata */ chunk->free_bytes += freed; /* update first free bit */ chunk_md->first_free = min(chunk_md->first_free, bit_off); pcpu_block_update_hint_free(chunk, bit_off, bits); pcpu_chunk_relocate(chunk, oslot); return freed; } static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits) { block->scan_hint = 0; block->contig_hint = nr_bits; block->left_free = nr_bits; block->right_free = nr_bits; block->first_free = 0; block->nr_bits = nr_bits; } static void pcpu_init_md_blocks(struct pcpu_chunk *chunk) { struct pcpu_block_md *md_block; /* init the chunk's block */ pcpu_init_md_block(&chunk->chunk_md, pcpu_chunk_map_bits(chunk)); for (md_block = chunk->md_blocks; md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk); md_block++) pcpu_init_md_block(md_block, PCPU_BITMAP_BLOCK_BITS); } /** * pcpu_alloc_first_chunk - creates chunks that serve the first chunk * @tmp_addr: the start of the region served * @map_size: size of the region served * * This is responsible for creating the chunks that serve the first chunk. The * base_addr is page aligned down of @tmp_addr while the region end is page * aligned up. Offsets are kept track of to determine the region served. All * this is done to appease the bitmap allocator in avoiding partial blocks. * * RETURNS: * Chunk serving the region at @tmp_addr of @map_size. */ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, int map_size) { struct pcpu_chunk *chunk; unsigned long aligned_addr; int start_offset, offset_bits, region_size, region_bits; size_t alloc_size; /* region calculations */ aligned_addr = tmp_addr & PAGE_MASK; start_offset = tmp_addr - aligned_addr; region_size = ALIGN(start_offset + map_size, PAGE_SIZE); /* allocate chunk */ alloc_size = struct_size(chunk, populated, BITS_TO_LONGS(region_size >> PAGE_SHIFT)); chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); INIT_LIST_HEAD(&chunk->list); chunk->base_addr = (void *)aligned_addr; chunk->start_offset = start_offset; chunk->end_offset = region_size - chunk->start_offset - map_size; chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]); chunk->alloc_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->alloc_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]); chunk->bound_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->bound_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]); chunk->md_blocks = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->md_blocks) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); #ifdef NEED_PCPUOBJ_EXT /* first chunk is free to use */ chunk->obj_exts = NULL; #endif pcpu_init_md_blocks(chunk); /* manage populated page bitmap */ chunk->immutable = true; bitmap_fill(chunk->populated, chunk->nr_pages); chunk->nr_populated = chunk->nr_pages; chunk->nr_empty_pop_pages = chunk->nr_pages; chunk->free_bytes = map_size; if (chunk->start_offset) { /* hide the beginning of the bitmap */ offset_bits = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, 0, offset_bits); set_bit(0, chunk->bound_map); set_bit(offset_bits, chunk->bound_map); chunk->chunk_md.first_free = offset_bits; pcpu_block_update_hint_alloc(chunk, 0, offset_bits); } if (chunk->end_offset) { /* hide the end of the bitmap */ offset_bits = chunk->end_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); set_bit((start_offset + map_size) / PCPU_MIN_ALLOC_SIZE, chunk->bound_map); set_bit(region_bits, chunk->bound_map); pcpu_block_update_hint_alloc(chunk, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); } return chunk; } static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; int region_bits; chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp); if (!chunk) return NULL; INIT_LIST_HEAD(&chunk->list); chunk->nr_pages = pcpu_unit_pages; region_bits = pcpu_chunk_map_bits(chunk); chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), gfp); if (!chunk->alloc_map) goto alloc_map_fail; chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), gfp); if (!chunk->bound_map) goto bound_map_fail; chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), gfp); if (!chunk->md_blocks) goto md_blocks_fail; #ifdef NEED_PCPUOBJ_EXT if (need_pcpuobj_ext()) { chunk->obj_exts = pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * sizeof(struct pcpuobj_ext), gfp); if (!chunk->obj_exts) goto objcg_fail; } #endif pcpu_init_md_blocks(chunk); /* init metadata */ chunk->free_bytes = chunk->nr_pages * PAGE_SIZE; return chunk; #ifdef NEED_PCPUOBJ_EXT objcg_fail: pcpu_mem_free(chunk->md_blocks); #endif md_blocks_fail: pcpu_mem_free(chunk->bound_map); bound_map_fail: pcpu_mem_free(chunk->alloc_map); alloc_map_fail: pcpu_mem_free(chunk); return NULL; } static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; #ifdef NEED_PCPUOBJ_EXT pcpu_mem_free(chunk->obj_exts); #endif pcpu_mem_free(chunk->md_blocks); pcpu_mem_free(chunk->bound_map); pcpu_mem_free(chunk->alloc_map); pcpu_mem_free(chunk); } /** * pcpu_chunk_populated - post-population bookkeeping * @chunk: pcpu_chunk which got populated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been populated to @chunk. Update * the bookkeeping information accordingly. Must be called after each * successful population. */ static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_set(chunk->populated, page_start, nr); chunk->nr_populated += nr; pcpu_nr_populated += nr; pcpu_update_empty_pages(chunk, nr); } /** * pcpu_chunk_depopulated - post-depopulation bookkeeping * @chunk: pcpu_chunk which got depopulated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been depopulated from @chunk. * Update the bookkeeping information accordingly. Must be called after * each successful depopulation. */ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_clear(chunk->populated, page_start, nr); chunk->nr_populated -= nr; pcpu_nr_populated -= nr; pcpu_update_empty_pages(chunk, -nr); } /* * Chunk management implementation. * * To allow different implementations, chunk alloc/free and * [de]population are implemented in a separate file which is pulled * into this file and compiled together. The following functions * should be implemented. * * pcpu_populate_chunk - populate the specified range of a chunk * pcpu_depopulate_chunk - depopulate the specified range of a chunk * pcpu_post_unmap_tlb_flush - flush tlb for the specified range of a chunk * pcpu_create_chunk - create a new chunk * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop * pcpu_addr_to_page - translate address to physical address * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp); static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end); static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end); static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); #ifdef CONFIG_NEED_PER_CPU_KM #include "percpu-km.c" #else #include "percpu-vm.c" #endif /** * pcpu_chunk_addr_search - determine chunk containing specified address * @addr: address for which the chunk needs to be determined. * * This is an internal function that handles all but static allocations. * Static percpu address values should never be passed into the allocator. * * RETURNS: * The address of the found chunk. */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { /* is it in the dynamic region (first chunk)? */ if (pcpu_addr_in_chunk(pcpu_first_chunk, addr)) return pcpu_first_chunk; /* is it in the reserved region? */ if (pcpu_addr_in_chunk(pcpu_reserved_chunk, addr)) return pcpu_reserved_chunk; /* * The address is relative to unit0 which might be unused and * thus unmapped. Offset the address to the unit space of the * current processor before looking it up in the vmalloc * space. Note that any possible cpu id can be used here, so * there's no need to worry about preemption or cpu hotplug. */ addr += pcpu_unit_offsets[raw_smp_processor_id()]; return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); } #ifdef CONFIG_MEMCG static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { struct obj_cgroup *objcg; if (!memcg_kmem_online() || !(gfp & __GFP_ACCOUNT)) return true; objcg = current_obj_cgroup(); if (!objcg) return true; if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size))) return false; *objcgp = objcg; return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { if (!objcg) return; if (likely(chunk && chunk->obj_exts)) { obj_cgroup_get(objcg); chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = objcg; rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, pcpu_obj_full_size(size)); rcu_read_unlock(); } else { obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); } } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { struct obj_cgroup *objcg; if (unlikely(!chunk->obj_exts)) return; objcg = chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup; if (!objcg) return; chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = NULL; obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, -pcpu_obj_full_size(size)); rcu_read_unlock(); obj_cgroup_put(objcg); } #else /* CONFIG_MEMCG */ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MEM_ALLOC_PROFILING static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, size_t size) { if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) { alloc_tag_add(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, current->alloc_tag, size); } } static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) alloc_tag_sub(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, size); } #else static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /** * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @reserved: allocate from the reserved chunk if available * @gfp: allocation flags * * Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN * then no warning will be triggered on invalid or failed allocation * requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, gfp_t gfp) { gfp_t pcpu_gfp; bool is_atomic; bool do_warn; struct obj_cgroup *objcg = NULL; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; const char *err; int slot, off, cpu, ret; unsigned long flags; void __percpu *ptr; size_t bits, bit_align; gfp = current_gfp_context(gfp); /* whitelisted flags that can be passed to the backing allocators */ pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; do_warn = !(gfp & __GFP_NOWARN); /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. * An allocation may have internal fragmentation from rounding up * of up to PCPU_MIN_ALLOC_SIZE - 1 bytes. */ if (unlikely(align < PCPU_MIN_ALLOC_SIZE)) align = PCPU_MIN_ALLOC_SIZE; size = ALIGN(size, PCPU_MIN_ALLOC_SIZE); bits = size >> PCPU_MIN_ALLOC_SHIFT; bit_align = align >> PCPU_MIN_ALLOC_SHIFT; if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE || !is_power_of_2(align))) { WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n", size, align); return NULL; } if (unlikely(!pcpu_memcg_pre_alloc_hook(size, gfp, &objcg))) return NULL; if (!is_atomic) { /* * pcpu_balance_workfn() allocates memory under this mutex, * and it may wait for memory reclaim. Allow current task * to become OOM victim, in case of memory pressure. */ if (gfp & __GFP_NOFAIL) { mutex_lock(&pcpu_alloc_mutex); } else if (mutex_lock_killable(&pcpu_alloc_mutex)) { pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } } spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ if (reserved && pcpu_reserved_chunk) { chunk = pcpu_reserved_chunk; off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { err = "alloc from reserved chunk failed"; goto fail_unlock; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) goto area_found; err = "alloc from reserved chunk failed"; goto fail_unlock; } restart: /* search through normal chunks */ for (slot = pcpu_size_to_slot(size); slot <= pcpu_free_slot; slot++) { list_for_each_entry_safe(chunk, next, &pcpu_chunk_lists[slot], list) { off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { if (slot < PCPU_SLOT_FAIL_THRESHOLD) pcpu_chunk_move(chunk, 0); continue; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) { pcpu_reintegrate_chunk(chunk); goto area_found; } } } spin_unlock_irqrestore(&pcpu_lock, flags); if (is_atomic) { err = "atomic alloc failed, no space left"; goto fail; } /* No space left. Create a new chunk. */ if (list_empty(&pcpu_chunk_lists[pcpu_free_slot])) { chunk = pcpu_create_chunk(pcpu_gfp); if (!chunk) { err = "failed to allocate new chunk"; goto fail; } spin_lock_irqsave(&pcpu_lock, flags); pcpu_chunk_relocate(chunk, -1); } else { spin_lock_irqsave(&pcpu_lock, flags); } goto restart; area_found: pcpu_stats_area_alloc(chunk, size); spin_unlock_irqrestore(&pcpu_lock, flags); /* populate if not all pages are already there */ if (!is_atomic) { unsigned int page_end, rs, re; rs = PFN_DOWN(off); page_end = PFN_UP(off + size); for_each_clear_bitrange_from(rs, re, chunk->populated, page_end) { WARN_ON(chunk->immutable); ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); spin_lock_irqsave(&pcpu_lock, flags); if (ret) { pcpu_free_area(chunk, off); err = "failed to populate"; goto fail_unlock; } pcpu_chunk_populated(chunk, rs, re); spin_unlock_irqrestore(&pcpu_lock, flags); } mutex_unlock(&pcpu_alloc_mutex); } if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); /* clear the areas and return address relative to base address */ for_each_possible_cpu(cpu) memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); kmemleak_alloc_percpu(ptr, size, gfp); trace_percpu_alloc_percpu(_RET_IP_, reserved, is_atomic, size, align, chunk->base_addr, off, ptr, pcpu_obj_full_size(size), gfp); pcpu_memcg_post_alloc_hook(objcg, chunk, off, size); pcpu_alloc_tag_alloc_hook(chunk, off, size); return ptr; fail_unlock: spin_unlock_irqrestore(&pcpu_lock, flags); fail: trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); if (do_warn && warn_limit) { pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", size, align, is_atomic, err); if (!is_atomic) dump_stack(); if (!--warn_limit) pr_info("limit reached, disable warning\n"); } if (is_atomic) { /* see the flag handling in pcpu_balance_workfn() */ pcpu_atomic_alloc_failed = true; pcpu_schedule_balance_work(); } else { mutex_unlock(&pcpu_alloc_mutex); } pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } EXPORT_SYMBOL_GPL(pcpu_alloc_noprof); /** * pcpu_balance_free - manage the amount of free chunks * @empty_only: free chunks only if there are no populated pages * * If empty_only is %false, reclaim all fully free chunks regardless of the * number of populated pages. Otherwise, only reclaim chunks that have no * populated pages. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_free(bool empty_only) { LIST_HEAD(to_free); struct list_head *free_head = &pcpu_chunk_lists[pcpu_free_slot]; struct pcpu_chunk *chunk, *next; lockdep_assert_held(&pcpu_lock); /* * There's no reason to keep around multiple unused chunks and VM * areas can be scarce. Destroy all free chunks except for one. */ list_for_each_entry_safe(chunk, next, free_head, list) { WARN_ON(chunk->immutable); /* spare the first one */ if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; if (!empty_only || chunk->nr_empty_pop_pages == 0) list_move(&chunk->list, &to_free); } if (list_empty(&to_free)) return; spin_unlock_irq(&pcpu_lock); list_for_each_entry_safe(chunk, next, &to_free, list) { unsigned int rs, re; for_each_set_bitrange(rs, re, chunk->populated, chunk->nr_pages) { pcpu_depopulate_chunk(chunk, rs, re); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, rs, re); spin_unlock_irq(&pcpu_lock); } pcpu_destroy_chunk(chunk); cond_resched(); } spin_lock_irq(&pcpu_lock); } /** * pcpu_balance_populated - manage the amount of populated pages * * Maintain a certain amount of populated pages to satisfy atomic allocations. * It is possible that this is called when physical memory is scarce causing * OOM killer to be triggered. We should avoid doing so until an actual * allocation causes the failure as it is possible that requests can be * serviced from already backed regions. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_populated(void) { /* gfp flags passed to underlying allocators */ const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; struct pcpu_chunk *chunk; int slot, nr_to_pop, ret; lockdep_assert_held(&pcpu_lock); /* * Ensure there are certain number of free populated pages for * atomic allocs. Fill up from the most packed so that atomic * allocs don't increase fragmentation. If atomic allocation * failed previously, always populate the maximum amount. This * should prevent atomic allocs larger than PAGE_SIZE from keeping * failing indefinitely; however, large atomic allocs are not * something we support properly and can be highly unreliable and * inefficient. */ retry_pop: if (pcpu_atomic_alloc_failed) { nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH; /* best effort anyway, don't worry about synchronization */ pcpu_atomic_alloc_failed = false; } else { nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - pcpu_nr_empty_pop_pages, 0, PCPU_EMPTY_POP_PAGES_HIGH); } for (slot = pcpu_size_to_slot(PAGE_SIZE); slot <= pcpu_free_slot; slot++) { unsigned int nr_unpop = 0, rs, re; if (!nr_to_pop) break; list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) { nr_unpop = chunk->nr_pages - chunk->nr_populated; if (nr_unpop) break; } if (!nr_unpop) continue; /* @chunk can't go away while pcpu_alloc_mutex is held */ for_each_clear_bitrange(rs, re, chunk->populated, chunk->nr_pages) { int nr = min_t(int, re - rs, nr_to_pop); spin_unlock_irq(&pcpu_lock); ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp); cond_resched(); spin_lock_irq(&pcpu_lock); if (!ret) { nr_to_pop -= nr; pcpu_chunk_populated(chunk, rs, rs + nr); } else { nr_to_pop = 0; } if (!nr_to_pop) break; } } if (nr_to_pop) { /* ran out of chunks to populate, create a new one and retry */ spin_unlock_irq(&pcpu_lock); chunk = pcpu_create_chunk(gfp); cond_resched(); spin_lock_irq(&pcpu_lock); if (chunk) { pcpu_chunk_relocate(chunk, -1); goto retry_pop; } } } /** * pcpu_reclaim_populated - scan over to_depopulate chunks and free empty pages * * Scan over chunks in the depopulate list and try to release unused populated * pages back to the system. Depopulated chunks are sidelined to prevent * repopulating these pages unless required. Fully free chunks are reintegrated * and freed accordingly (1 is kept around). If we drop below the empty * populated pages threshold, reintegrate the chunk if it has empty free pages. * Each chunk is scanned in the reverse order to keep populated pages close to * the beginning of the chunk. * * CONTEXT: * pcpu_lock (can be dropped temporarily) * */ static void pcpu_reclaim_populated(void) { struct pcpu_chunk *chunk; struct pcpu_block_md *block; int freed_page_start, freed_page_end; int i, end; bool reintegrate; lockdep_assert_held(&pcpu_lock); /* * Once a chunk is isolated to the to_depopulate list, the chunk is no * longer discoverable to allocations whom may populate pages. The only * other accessor is the free path which only returns area back to the * allocator not touching the populated bitmap. */ while ((chunk = list_first_entry_or_null( &pcpu_chunk_lists[pcpu_to_depopulate_slot], struct pcpu_chunk, list))) { WARN_ON(chunk->immutable); /* * Scan chunk's pages in the reverse order to keep populated * pages close to the beginning of the chunk. */ freed_page_start = chunk->nr_pages; freed_page_end = 0; reintegrate = false; for (i = chunk->nr_pages - 1, end = -1; i >= 0; i--) { /* no more work to do */ if (chunk->nr_empty_pop_pages == 0) break; /* reintegrate chunk to prevent atomic alloc failures */ if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_HIGH) { reintegrate = true; break; } /* * If the page is empty and populated, start or * extend the (i, end) range. If i == 0, decrease * i and perform the depopulation to cover the last * (first) page in the chunk. */ block = chunk->md_blocks + i; if (block->contig_hint == PCPU_BITMAP_BLOCK_BITS && test_bit(i, chunk->populated)) { if (end == -1) end = i; if (i > 0) continue; i--; } /* depopulate if there is an active range */ if (end == -1) continue; spin_unlock_irq(&pcpu_lock); pcpu_depopulate_chunk(chunk, i + 1, end + 1); cond_resched(); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, i + 1, end + 1); freed_page_start = min(freed_page_start, i + 1); freed_page_end = max(freed_page_end, end + 1); /* reset the range and continue */ end = -1; } /* batch tlb flush per chunk to amortize cost */ if (freed_page_start < freed_page_end) { spin_unlock_irq(&pcpu_lock); pcpu_post_unmap_tlb_flush(chunk, freed_page_start, freed_page_end); cond_resched(); spin_lock_irq(&pcpu_lock); } if (reintegrate || chunk->free_bytes == pcpu_unit_size) pcpu_reintegrate_chunk(chunk); else list_move_tail(&chunk->list, &pcpu_chunk_lists[pcpu_sidelined_slot]); } } /** * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * * For each chunk type, manage the number of fully free chunks and the number of * populated pages. An important thing to consider is when pages are freed and * how they contribute to the global counts. */ static void pcpu_balance_workfn(struct work_struct *work) { /* * pcpu_balance_free() is called twice because the first time we may * trim pages in the active pcpu_nr_empty_pop_pages which may cause us * to grow other chunks. This then gives pcpu_reclaim_populated() time * to move fully free chunks to the active list to be freed if * appropriate. */ mutex_lock(&pcpu_alloc_mutex); spin_lock_irq(&pcpu_lock); pcpu_balance_free(false); pcpu_reclaim_populated(); pcpu_balance_populated(); pcpu_balance_free(true); spin_unlock_irq(&pcpu_lock); mutex_unlock(&pcpu_alloc_mutex); } /** * pcpu_alloc_size - the size of the dynamic percpu area * @ptr: pointer to the dynamic percpu area * * Returns the size of the @ptr allocation. This is undefined for statically * defined percpu variables as there is no corresponding chunk->bound_map. * * RETURNS: * The size of the dynamic percpu area. * * CONTEXT: * Can be called from atomic context. */ size_t pcpu_alloc_size(void __percpu *ptr) { struct pcpu_chunk *chunk; unsigned long bit_off, end; void *addr; if (!ptr) return 0; addr = __pcpu_ptr_to_addr(ptr); /* No pcpu_lock here: ptr has not been freed, so chunk is still alive */ chunk = pcpu_chunk_addr_search(addr); bit_off = (addr - chunk->base_addr) / PCPU_MIN_ALLOC_SIZE; end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), bit_off + 1); return (end - bit_off) * PCPU_MIN_ALLOC_SIZE; } /** * free_percpu - free percpu area * @ptr: pointer to area to free * * Free percpu area @ptr. * * CONTEXT: * Can be called from atomic context. */ void free_percpu(void __percpu *ptr) { void *addr; struct pcpu_chunk *chunk; unsigned long flags; int size, off; bool need_balance = false; if (!ptr) return; kmemleak_free_percpu(ptr); addr = __pcpu_ptr_to_addr(ptr); chunk = pcpu_chunk_addr_search(addr); off = addr - chunk->base_addr; spin_lock_irqsave(&pcpu_lock, flags); size = pcpu_free_area(chunk, off); pcpu_alloc_tag_free_hook(chunk, off, size); pcpu_memcg_free_hook(chunk, off, size); /* * If there are more than one fully free chunks, wake up grim reaper. * If the chunk is isolated, it may be in the process of being * reclaimed. Let reclaim manage cleaning up of that chunk. */ if (!chunk->isolated && chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; list_for_each_entry(pos, &pcpu_chunk_lists[pcpu_free_slot], list) if (pos != chunk) { need_balance = true; break; } } else if (pcpu_should_reclaim_chunk(chunk)) { pcpu_isolate_chunk(chunk); need_balance = true; } trace_percpu_free_percpu(chunk->base_addr, off, ptr); spin_unlock_irqrestore(&pcpu_lock, flags); if (need_balance) pcpu_schedule_balance_work(); } EXPORT_SYMBOL_GPL(free_percpu); bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) { #ifdef CONFIG_SMP const size_t static_size = __per_cpu_end - __per_cpu_start; void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); unsigned int cpu; for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); void *va = (void *)addr; if (va >= start && va < start + static_size) { if (can_addr) { *can_addr = (unsigned long) (va - start); *can_addr += (unsigned long) per_cpu_ptr(base, get_boot_cpu_id()); } return true; } } #endif /* on UP, can't distinguish from other static vars, always false */ return false; } /** * is_kernel_percpu_address - test whether address is from static percpu area * @addr: address to test * * Test whether @addr belongs to in-kernel static percpu area. Module * static percpu areas are not considered. For those, use * is_module_percpu_address(). * * RETURNS: * %true if @addr is from in-kernel static percpu area, %false otherwise. */ bool is_kernel_percpu_address(unsigned long addr) { return __is_kernel_percpu_address(addr, NULL); } /** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * * Given @addr which is dereferenceable address obtained via one of * percpu access macros, this function translates it into its physical * address. The caller is responsible for ensuring @addr stays valid * until this function finishes. * * percpu allocator has special setup for the first chunk, which currently * supports either embedding in linear address space or vmalloc mapping, * and, from the second one, the backing allocator (currently either vm or * km) provides translation. * * The addr can be translated simply without checking if it falls into the * first chunk. But the current code reflects better how percpu allocator * actually works, and the verification can discover both bugs in percpu * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current * code. * * RETURNS: * The physical address for @addr. */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); bool in_first_chunk = false; unsigned long first_low, first_high; unsigned int cpu; /* * The following test on unit_low/high isn't strictly * necessary but will speed up lookups of addresses which * aren't in the first chunk. * * The address check is against full chunk sizes. pcpu_base_addr * points to the beginning of the first chunk including the * static region. Assumes good intent as the first chunk may * not be full (ie. < pcpu_unit_pages in size). */ first_low = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_low_unit_cpu, 0); first_high = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_high_unit_cpu, pcpu_unit_pages); if ((unsigned long)addr >= first_low && (unsigned long)addr < first_high) { for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); if (addr >= start && addr < start + pcpu_unit_size) { in_first_chunk = true; break; } } } if (in_first_chunk) { if (!is_vmalloc_addr(addr)) return __pa(addr); else return page_to_phys(vmalloc_to_page(addr)) + offset_in_page(addr); } else return page_to_phys(pcpu_addr_to_page(addr)) + offset_in_page(addr); } /** * pcpu_alloc_alloc_info - allocate percpu allocation info * @nr_groups: the number of groups * @nr_units: the number of units * * Allocate ai which is large enough for @nr_groups groups containing * @nr_units units. The returned ai's groups[0].cpu_map points to the * cpu_map array which is long enough for @nr_units and filled with * NR_CPUS. It's the caller's responsibility to initialize cpu_map * pointer of other groups. * * RETURNS: * Pointer to the allocated pcpu_alloc_info on success, NULL on * failure. */ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, int nr_units) { struct pcpu_alloc_info *ai; size_t base_size, ai_size; void *ptr; int unit; base_size = ALIGN(struct_size(ai, groups, nr_groups), __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); ptr = memblock_alloc(PFN_ALIGN(ai_size), PAGE_SIZE); if (!ptr) return NULL; ai = ptr; ptr += base_size; ai->groups[0].cpu_map = ptr; for (unit = 0; unit < nr_units; unit++) ai->groups[0].cpu_map[unit] = NR_CPUS; ai->nr_groups = nr_groups; ai->__ai_size = PFN_ALIGN(ai_size); return ai; } /** * pcpu_free_alloc_info - free percpu allocation info * @ai: pcpu_alloc_info to free * * Free @ai which was allocated by pcpu_alloc_alloc_info(). */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { memblock_free(ai, ai->__ai_size); } /** * pcpu_dump_alloc_info - print out information about pcpu_alloc_info * @lvl: loglevel * @ai: allocation info to dump * * Print out information about @ai using loglevel @lvl. */ static void pcpu_dump_alloc_info(const char *lvl, const struct pcpu_alloc_info *ai) { int group_width = 1, cpu_width = 1, width; char empty_str[] = "--------"; int alloc = 0, alloc_end = 0; int group, v; int upa, apl; /* units per alloc, allocs per line */ v = ai->nr_groups; while (v /= 10) group_width++; v = num_possible_cpus(); while (v /= 10) cpu_width++; empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0'; upa = ai->alloc_size / ai->unit_size; width = upa * (cpu_width + 1) + group_width + 3; apl = rounddown_pow_of_two(max(60 / width, 1)); printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu", lvl, ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size); for (group = 0; group < ai->nr_groups; group++) { const struct pcpu_group_info *gi = &ai->groups[group]; int unit = 0, unit_end = 0; BUG_ON(gi->nr_units % upa); for (alloc_end += gi->nr_units / upa; alloc < alloc_end; alloc++) { if (!(alloc % apl)) { pr_cont("\n"); printk("%spcpu-alloc: ", lvl); } pr_cont("[%0*d] ", group_width, group); for (unit_end += upa; unit < unit_end; unit++) if (gi->cpu_map[unit] != NR_CPUS) pr_cont("%0*d ", cpu_width, gi->cpu_map[unit]); else pr_cont("%s ", empty_str); } } pr_cont("\n"); } /** * pcpu_setup_first_chunk - initialize the first percpu chunk * @ai: pcpu_alloc_info describing how to percpu area is shaped * @base_addr: mapped address * * Initialize the first percpu chunk which contains the kernel static * percpu area. This function is to be called from arch percpu area * setup path. * * @ai contains all information necessary to initialize the first * chunk and prime the dynamic percpu allocator. * * @ai->static_size is the size of static percpu area. * * @ai->reserved_size, if non-zero, specifies the amount of bytes to * reserve after the static area in the first chunk. This reserves * the first chunk such that it's available only through reserved * percpu allocation. This is primarily used to serve module percpu * static areas on architectures where the addressing model has * limited offset range for symbol relocations to guarantee module * percpu symbols fall inside the relocatable range. * * @ai->dyn_size determines the number of bytes available for dynamic * allocation in the first chunk. The area between @ai->static_size + * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused. * * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE * and equal to or larger than @ai->static_size + @ai->reserved_size + * @ai->dyn_size. * * @ai->atom_size is the allocation atom size and used as alignment * for vm areas. * * @ai->alloc_size is the allocation size and always multiple of * @ai->atom_size. This is larger than @ai->atom_size if * @ai->unit_size is larger than @ai->atom_size. * * @ai->nr_groups and @ai->groups describe virtual memory layout of * percpu areas. Units which should be colocated are put into the * same group. Dynamic VM areas will be allocated according to these * groupings. If @ai->nr_groups is zero, a single group containing * all units is assumed. * * The caller should have mapped the first chunk at @base_addr and * copied static data to each unit. * * The first chunk will always contain a static and a dynamic region. * However, the static region is not managed by any chunk. If the first * chunk also contains a reserved region, it is served by two chunks - * one for the reserved region and one for the dynamic region. They * share the same vm, but use offset regions in the area allocation map. * The chunk serving the dynamic region is circulated in the chunk slots * and available for dynamic allocation like any other chunk. */ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr) { size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; size_t static_size, dyn_size; unsigned long *group_offsets; size_t *group_sizes; unsigned long *unit_off; unsigned int cpu; int *unit_map; int group, unit, i; unsigned long tmp_addr; size_t alloc_size; #define PCPU_SETUP_BUG_ON(cond) do { \ if (unlikely(cond)) { \ pr_emerg("failed to initialize, %s\n", #cond); \ pr_emerg("cpu_possible_mask=%*pb\n", \ cpumask_pr_args(cpu_possible_mask)); \ pcpu_dump_alloc_info(KERN_EMERG, ai); \ BUG(); \ } \ } while (0) /* sanity checks */ PCPU_SETUP_BUG_ON(ai->nr_groups <= 0); #ifdef CONFIG_SMP PCPU_SETUP_BUG_ON(!ai->static_size); PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start)); #endif PCPU_SETUP_BUG_ON(!base_addr); PCPU_SETUP_BUG_ON(offset_in_page(base_addr)); PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size)); PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->unit_size, PCPU_BITMAP_BLOCK_SIZE)); PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->reserved_size, PCPU_MIN_ALLOC_SIZE)); PCPU_SETUP_BUG_ON(!(IS_ALIGNED(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) || IS_ALIGNED(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE))); PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ alloc_size = ai->nr_groups * sizeof(group_offsets[0]); group_offsets = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!group_offsets) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = ai->nr_groups * sizeof(group_sizes[0]); group_sizes = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!group_sizes) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = nr_cpu_ids * sizeof(unit_map[0]); unit_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!unit_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = nr_cpu_ids * sizeof(unit_off[0]); unit_off = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!unit_off) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; pcpu_low_unit_cpu = NR_CPUS; pcpu_high_unit_cpu = NR_CPUS; for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) { const struct pcpu_group_info *gi = &ai->groups[group]; group_offsets[group] = gi->base_offset; group_sizes[group] = gi->nr_units * ai->unit_size; for (i = 0; i < gi->nr_units; i++) { cpu = gi->cpu_map[i]; if (cpu == NR_CPUS) continue; PCPU_SETUP_BUG_ON(cpu >= nr_cpu_ids); PCPU_SETUP_BUG_ON(!cpu_possible(cpu)); PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX); unit_map[cpu] = unit + i; unit_off[cpu] = gi->base_offset + i * ai->unit_size; /* determine low/high unit_cpu */ if (pcpu_low_unit_cpu == NR_CPUS || unit_off[cpu] < unit_off[pcpu_low_unit_cpu]) pcpu_low_unit_cpu = cpu; if (pcpu_high_unit_cpu == NR_CPUS || unit_off[cpu] > unit_off[pcpu_high_unit_cpu]) pcpu_high_unit_cpu = cpu; } } pcpu_nr_units = unit; for_each_possible_cpu(cpu) PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX); /* we're done parsing the input, undefine BUG macro and dump config */ #undef PCPU_SETUP_BUG_ON pcpu_dump_alloc_info(KERN_DEBUG, ai); pcpu_nr_groups = ai->nr_groups; pcpu_group_offsets = group_offsets; pcpu_group_sizes = group_sizes; pcpu_unit_map = unit_map; pcpu_unit_offsets = unit_off; /* determine basic parameters */ pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_atom_size = ai->atom_size; pcpu_chunk_struct_size = struct_size((struct pcpu_chunk *)0, populated, BITS_TO_LONGS(pcpu_unit_pages)); pcpu_stats_save_ai(ai); /* * Allocate chunk slots. The slots after the active slots are: * sidelined_slot - isolated, depopulated chunks * free_slot - fully free chunks * to_depopulate_slot - isolated, chunks to depopulate */ pcpu_sidelined_slot = __pcpu_size_to_slot(pcpu_unit_size) + 1; pcpu_free_slot = pcpu_sidelined_slot + 1; pcpu_to_depopulate_slot = pcpu_free_slot + 1; pcpu_nr_slots = pcpu_to_depopulate_slot + 1; pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]), SMP_CACHE_BYTES); if (!pcpu_chunk_lists) panic("%s: Failed to allocate %zu bytes\n", __func__, pcpu_nr_slots * sizeof(pcpu_chunk_lists[0])); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_chunk_lists[i]); /* * The end of the static region needs to be aligned with the * minimum allocation size as this offsets the reserved and * dynamic region. The first chunk ends page aligned by * expanding the dynamic region, therefore the dynamic region * can be shrunk to compensate while still staying above the * configured sizes. */ static_size = ALIGN(ai->static_size, PCPU_MIN_ALLOC_SIZE); dyn_size = ai->dyn_size - (static_size - ai->static_size); /* * Initialize first chunk: * This chunk is broken up into 3 parts: * < static | [reserved] | dynamic > * - static - there is no backing chunk because these allocations can * never be freed. * - reserved (pcpu_reserved_chunk) - exists primarily to serve * allocations from module load. * - dynamic (pcpu_first_chunk) - serves the dynamic part of the first * chunk. */ tmp_addr = (unsigned long)base_addr + static_size; if (ai->reserved_size) pcpu_reserved_chunk = pcpu_alloc_first_chunk(tmp_addr, ai->reserved_size); tmp_addr = (unsigned long)base_addr + static_size + ai->reserved_size; pcpu_first_chunk = pcpu_alloc_first_chunk(tmp_addr, dyn_size); pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* include all regions of the first chunk */ pcpu_nr_populated += PFN_DOWN(size_sum); pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(base_addr); /* we're done */ pcpu_base_addr = base_addr; } #ifdef CONFIG_SMP const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = { [PCPU_FC_AUTO] = "auto", [PCPU_FC_EMBED] = "embed", [PCPU_FC_PAGE] = "page", }; enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO; static int __init percpu_alloc_setup(char *str) { if (!str) return -EINVAL; if (0) /* nada */; #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK else if (!strcmp(str, "embed")) pcpu_chosen_fc = PCPU_FC_EMBED; #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK else if (!strcmp(str, "page")) pcpu_chosen_fc = PCPU_FC_PAGE; #endif else pr_warn("unknown allocator %s specified\n", str); return 0; } early_param("percpu_alloc", percpu_alloc_setup); /* * pcpu_embed_first_chunk() is used by the generic percpu setup. * Build it if needed by the arch config or the generic setup is going * to be used. */ #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \ !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) #define BUILD_EMBED_FIRST_CHUNK #endif /* build pcpu_page_first_chunk() iff needed by the arch config */ #if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) #define BUILD_PAGE_FIRST_CHUNK #endif /* pcpu_build_alloc_info() is used by both embed and page first chunk */ #if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK) /** * pcpu_build_alloc_info - build alloc_info considering distances between CPUs * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * * This function determines grouping of units, their mappings to cpus * and other parameters considering needed percpu size, allocation * atom size and distances between CPUs. * * Groups are always multiples of atom size and CPUs which are of * LOCAL_DISTANCE both ways are grouped together and share space for * units in the same group. The returned configuration is guaranteed * to have CPUs on different nodes on different groups and >=75% usage * of allocated virtual address space. * * RETURNS: * On success, pointer to the new allocation_info is returned. On * failure, ERR_PTR value is returned. */ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn) { static int group_map[NR_CPUS] __initdata; static int group_cnt[NR_CPUS] __initdata; static struct cpumask mask __initdata; const size_t static_size = __per_cpu_end - __per_cpu_start; int nr_groups = 1, nr_units = 0; size_t size_sum, min_unit_size, alloc_size; int upa, max_upa, best_upa; /* units_per_alloc */ int last_allocs, group, unit; unsigned int cpu, tcpu; struct pcpu_alloc_info *ai; unsigned int *cpu_map; /* this function may be called multiple times */ memset(group_map, 0, sizeof(group_map)); memset(group_cnt, 0, sizeof(group_cnt)); cpumask_clear(&mask); /* calculate size_sum and ensure dyn_size is enough for early alloc */ size_sum = PFN_ALIGN(static_size + reserved_size + max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE)); dyn_size = size_sum - static_size - reserved_size; /* * Determine min_unit_size, alloc_size and max_upa such that * alloc_size is multiple of atom_size and is the smallest * which can accommodate 4k aligned segments which are equal to * or larger than min_unit_size. */ min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); /* determine the maximum # of units that can fit in an allocation */ alloc_size = roundup(min_unit_size, atom_size); upa = alloc_size / min_unit_size; while (alloc_size % upa || (offset_in_page(alloc_size / upa))) upa--; max_upa = upa; cpumask_copy(&mask, cpu_possible_mask); /* group cpus according to their proximity */ for (group = 0; !cpumask_empty(&mask); group++) { /* pop the group's first cpu */ cpu = cpumask_first(&mask); group_map[cpu] = group; group_cnt[group]++; cpumask_clear_cpu(cpu, &mask); for_each_cpu(tcpu, &mask) { if (!cpu_distance_fn || (cpu_distance_fn(cpu, tcpu) == LOCAL_DISTANCE && cpu_distance_fn(tcpu, cpu) == LOCAL_DISTANCE)) { group_map[tcpu] = group; group_cnt[group]++; cpumask_clear_cpu(tcpu, &mask); } } } nr_groups = group; /* * Wasted space is caused by a ratio imbalance of upa to group_cnt. * Expand the unit_size until we use >= 75% of the units allocated. * Related to atom_size, which could be much larger than the unit_size. */ last_allocs = INT_MAX; best_upa = 0; for (upa = max_upa; upa; upa--) { int allocs = 0, wasted = 0; if (alloc_size % upa || (offset_in_page(alloc_size / upa))) continue; for (group = 0; group < nr_groups; group++) { int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); allocs += this_allocs; wasted += this_allocs * upa - group_cnt[group]; } /* * Don't accept if wastage is over 1/3. The * greater-than comparison ensures upa==1 always * passes the following check. */ if (wasted > num_possible_cpus() / 3) continue; /* and then don't consume more memory */ if (allocs > last_allocs) break; last_allocs = allocs; best_upa = upa; } BUG_ON(!best_upa); upa = best_upa; /* allocate and fill alloc_info */ for (group = 0; group < nr_groups; group++) nr_units += roundup(group_cnt[group], upa); ai = pcpu_alloc_alloc_info(nr_groups, nr_units); if (!ai) return ERR_PTR(-ENOMEM); cpu_map = ai->groups[0].cpu_map; for (group = 0; group < nr_groups; group++) { ai->groups[group].cpu_map = cpu_map; cpu_map += roundup(group_cnt[group], upa); } ai->static_size = static_size; ai->reserved_size = reserved_size; ai->dyn_size = dyn_size; ai->unit_size = alloc_size / upa; ai->atom_size = atom_size; ai->alloc_size = alloc_size; for (group = 0, unit = 0; group < nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; /* * Initialize base_offset as if all groups are located * back-to-back. The caller should update this to * reflect actual allocation. */ gi->base_offset = unit * ai->unit_size; for_each_possible_cpu(cpu) if (group_map[cpu] == group) gi->cpu_map[gi->nr_units++] = cpu; gi->nr_units = roundup(gi->nr_units, upa); unit += gi->nr_units; } BUG_ON(unit != nr_units); return ai; } static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); #ifdef CONFIG_NUMA int node = NUMA_NO_NODE; void *ptr; if (cpu_to_nd_fn) node = cpu_to_nd_fn(cpu); if (node == NUMA_NO_NODE || !node_online(node) || !NODE_DATA(node)) { ptr = memblock_alloc_from(size, align, goal); pr_info("cpu %d has no node %d or node-local memory\n", cpu, node); pr_debug("per cpu data for cpu%d %zu bytes at 0x%llx\n", cpu, size, (u64)__pa(ptr)); } else { ptr = memblock_alloc_try_nid(size, align, goal, MEMBLOCK_ALLOC_ACCESSIBLE, node); pr_debug("per cpu data for cpu%d %zu bytes on node%d at 0x%llx\n", cpu, size, node, (u64)__pa(ptr)); } return ptr; #else return memblock_alloc_from(size, align, goal); #endif } static void __init pcpu_fc_free(void *ptr, size_t size) { memblock_free(ptr, size); } #endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ #if defined(BUILD_EMBED_FIRST_CHUNK) /** * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated * by calling pcpu_fc_alloc and used as-is without being mapped into * vmalloc area. Allocations are always whole multiples of @atom_size * aligned to @atom_size. * * This enables the first chunk to piggy back on the linear physical * mapping which often uses larger page size. Please note that this * can result in very sparse cpu->unit mapping on NUMA machines thus * requiring large vmalloc address space. Don't use this allocator if * vmalloc space is not orders of magnitude larger than distances * between node memory addresses (ie. 32bit NUMA machines). * * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit * size, the leftover is returned using pcpu_fc_free. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { void *base = (void *)ULONG_MAX; void **areas = NULL; struct pcpu_alloc_info *ai; size_t size_sum, areas_size; unsigned long max_distance; int group, i, highest_group, rc = 0; ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, cpu_distance_fn); if (IS_ERR(ai)) return PTR_ERR(ai); size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); areas = memblock_alloc(areas_size, SMP_CACHE_BYTES); if (!areas) { rc = -ENOMEM; goto out_free; } /* allocate, copy and determine base address & max_distance */ highest_group = 0; for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; unsigned int cpu = NR_CPUS; void *ptr; for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++) cpu = gi->cpu_map[i]; BUG_ON(cpu == NR_CPUS); /* allocate space for the whole group */ ptr = pcpu_fc_alloc(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn); if (!ptr) { rc = -ENOMEM; goto out_free_areas; } /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(ptr)); areas[group] = ptr; base = min(ptr, base); if (ptr > areas[highest_group]) highest_group = group; } max_distance = areas[highest_group] - base; max_distance += ai->unit_size * ai->groups[highest_group].nr_units; /* warn if maximum distance is further than 75% of vmalloc space */ if (max_distance > VMALLOC_TOTAL * 3 / 4) { pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n", max_distance, VMALLOC_TOTAL); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK /* and fail if we have fallback */ rc = -EINVAL; goto out_free_areas; #endif } /* * Copy data and free unused parts. This should happen after all * allocations are complete; otherwise, we may end up with * overlapping groups. */ for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; void *ptr = areas[group]; for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { if (gi->cpu_map[i] == NR_CPUS) { /* unused unit, free whole */ pcpu_fc_free(ptr, ai->unit_size); continue; } /* copy and return the unused part */ memcpy(ptr, __per_cpu_load, ai->static_size); pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum); } } /* base address is now known, determine group base offsets */ for (group = 0; group < ai->nr_groups; group++) { ai->groups[group].base_offset = areas[group] - base; } pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); pcpu_setup_first_chunk(ai, base); goto out_free; out_free_areas: for (group = 0; group < ai->nr_groups; group++) if (areas[group]) pcpu_fc_free(areas[group], ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); if (areas) memblock_free(areas, areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK #include <asm/pgalloc.h> #ifndef P4D_TABLE_SIZE #define P4D_TABLE_SIZE PAGE_SIZE #endif #ifndef PUD_TABLE_SIZE #define PUD_TABLE_SIZE PAGE_SIZE #endif #ifndef PMD_TABLE_SIZE #define PMD_TABLE_SIZE PAGE_SIZE #endif #ifndef PTE_TABLE_SIZE #define PTE_TABLE_SIZE PAGE_SIZE #endif void __init __weak pcpu_populate_pte(unsigned long addr) { pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; pmd_t *pmd; if (pgd_none(*pgd)) { p4d = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE); if (!p4d) goto err_alloc; pgd_populate(&init_mm, pgd, p4d); } p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { pud = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); if (!pud) goto err_alloc; p4d_populate(&init_mm, p4d, pud); } pud = pud_offset(p4d, addr); if (pud_none(*pud)) { pmd = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); if (!pmd) goto err_alloc; pud_populate(&init_mm, pud, pmd); } pmd = pmd_offset(pud, addr); if (!pmd_present(*pmd)) { pte_t *new; new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); if (!new) goto err_alloc; pmd_populate_kernel(&init_mm, pmd, new); } return; err_alloc: panic("%s: Failed to allocate memory\n", __func__); } /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up page-remapped first percpu * chunk and can be called where pcpu_setup_first_chunk() is expected. * * This is the basic allocator. Static percpu area is allocated * page-by-page into vmalloc area. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { static struct vm_struct vm; struct pcpu_alloc_info *ai; char psize_str[16]; int unit_pages; size_t pages_size; struct page **pages; int unit, i, j, rc = 0; int upa; int nr_g0_units; snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL); if (IS_ERR(ai)) return PTR_ERR(ai); BUG_ON(ai->nr_groups != 1); upa = ai->alloc_size/ai->unit_size; nr_g0_units = roundup(num_possible_cpus(), upa); if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { pcpu_free_alloc_info(ai); return -EINVAL; } unit_pages = ai->unit_size >> PAGE_SHIFT; /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); pages = memblock_alloc(pages_size, SMP_CACHE_BYTES); if (!pages) panic("%s: Failed to allocate %zu bytes\n", __func__, pages_size); /* allocate pages */ j = 0; for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned int cpu = ai->groups[0].cpu_map[unit]; for (i = 0; i < unit_pages; i++) { void *ptr; ptr = pcpu_fc_alloc(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn); if (!ptr) { pr_warn("failed to allocate %s page for cpu%u\n", psize_str, cpu); goto enomem; } /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(ptr)); pages[j++] = virt_to_page(ptr); } } /* allocate vm area, map the pages and copy static data */ vm.flags = VM_ALLOC; vm.size = num_possible_cpus() * ai->unit_size; vm_area_register_early(&vm, PAGE_SIZE); for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned long unit_addr = (unsigned long)vm.addr + unit * ai->unit_size; for (i = 0; i < unit_pages; i++) pcpu_populate_pte(unit_addr + (i << PAGE_SHIFT)); /* pte already populated, the following shouldn't fail */ rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], unit_pages); if (rc < 0) panic("failed to map percpu area, err=%d\n", rc); flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size); /* copy static data */ memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); } /* we're ready, commit */ pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); pcpu_setup_first_chunk(ai, vm.addr); goto out_free_ar; enomem: while (--j >= 0) pcpu_fc_free(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: memblock_free(pages, pages_size); pcpu_free_alloc_info(ai); return rc; } #endif /* BUILD_PAGE_FIRST_CHUNK */ #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA /* * Generic SMP percpu area setup. * * The embedding helper is used because its behavior closely resembles * the original non-dynamic generic percpu area setup. This is * important because many archs have addressing restrictions and might * fail if the percpu area is located far away from the previous * location. As an added bonus, in non-NUMA cases, embedding is * generally a good idea TLB-wise because percpu area can piggy back * on the physical linear memory mapping which uses large page * mappings on applicable archs. */ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); void __init setup_per_cpu_areas(void) { unsigned long delta; unsigned int cpu; int rc; /* * Always reserve area for module percpu variables. That's * what the legacy allocator did. */ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, NULL); if (rc < 0) panic("Failed to initialize percpu areas."); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; } #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ #else /* CONFIG_SMP */ /* * UP percpu area setup. * * UP always uses km-based percpu allocator with identity mapping. * Static percpu variables are indistinguishable from the usual static * variables and don't require any special preparation. */ void __init setup_per_cpu_areas(void) { const size_t unit_size = roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE, PERCPU_DYNAMIC_RESERVE)); struct pcpu_alloc_info *ai; void *fc; ai = pcpu_alloc_alloc_info(1, 1); fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(fc)); ai->dyn_size = unit_size; ai->unit_size = unit_size; ai->atom_size = unit_size; ai->alloc_size = unit_size; ai->groups[0].nr_units = 1; ai->groups[0].cpu_map[0] = 0; pcpu_setup_first_chunk(ai, fc); pcpu_free_alloc_info(ai); } #endif /* CONFIG_SMP */ /* * pcpu_nr_pages - calculate total number of populated backing pages * * This reflects the number of pages populated to back chunks. Metadata is * excluded in the number exposed in meminfo as the number of backing pages * scales with the number of cpus and can quickly outweigh the memory used for * metadata. It also keeps this calculation nice and simple. * * RETURNS: * Total number of populated backing pages in use by the allocator. */ unsigned long pcpu_nr_pages(void) { return pcpu_nr_populated * pcpu_nr_units; } /* * Percpu allocator is initialized early during boot when neither slab or * workqueue is available. Plug async management until everything is up * and running. */ static int __init percpu_enable_async(void) { pcpu_async_enabled = true; return 0; } subsys_initcall(percpu_enable_async); |
| 59 245 225 226 224 226 169 212 211 132 116 115 76 43 43 39 43 85 85 9 76 9 34 1 85 9 76 9 83 84 59 39 2 13 13 35 76 47 37 245 56 51 20 210 52 4 7 210 227 227 227 30 196 50 53 53 226 2 196 196 196 24 171 53 18 40 40 56 38 156 157 117 117 38 117 17 99 36 38 117 17 99 36 22 95 94 95 117 117 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/unicode.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Handler routines for unicode strings */ #include <linux/types.h> #include <linux/nls.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" /* Fold the case of a unicode char, given the 16 bit value */ /* Returns folded char, or 0 if ignorable */ static inline u16 case_fold(u16 c) { u16 tmp; tmp = hfsplus_case_fold_table[c >> 8]; if (tmp) tmp = hfsplus_case_fold_table[tmp + (c & 0xff)]; else tmp = c; return tmp; } /* Compare unicode strings, return values like normal strcmp */ int hfsplus_strcasecmp(const struct hfsplus_unistr *s1, const struct hfsplus_unistr *s2) { u16 len1, len2, c1, c2; const hfsplus_unichr *p1, *p2; len1 = be16_to_cpu(s1->length); len2 = be16_to_cpu(s2->length); p1 = s1->unicode; p2 = s2->unicode; while (1) { c1 = c2 = 0; while (len1 && !c1) { c1 = case_fold(be16_to_cpu(*p1)); p1++; len1--; } while (len2 && !c2) { c2 = case_fold(be16_to_cpu(*p2)); p2++; len2--; } if (c1 != c2) return (c1 < c2) ? -1 : 1; if (!c1 && !c2) return 0; } } /* Compare names as a sequence of 16-bit unsigned integers */ int hfsplus_strcmp(const struct hfsplus_unistr *s1, const struct hfsplus_unistr *s2) { u16 len1, len2, c1, c2; const hfsplus_unichr *p1, *p2; int len; len1 = be16_to_cpu(s1->length); len2 = be16_to_cpu(s2->length); p1 = s1->unicode; p2 = s2->unicode; for (len = min(len1, len2); len > 0; len--) { c1 = be16_to_cpu(*p1); c2 = be16_to_cpu(*p2); if (c1 != c2) return c1 < c2 ? -1 : 1; p1++; p2++; } return len1 < len2 ? -1 : len1 > len2 ? 1 : 0; } #define Hangul_SBase 0xac00 #define Hangul_LBase 0x1100 #define Hangul_VBase 0x1161 #define Hangul_TBase 0x11a7 #define Hangul_SCount 11172 #define Hangul_LCount 19 #define Hangul_VCount 21 #define Hangul_TCount 28 #define Hangul_NCount (Hangul_VCount * Hangul_TCount) static u16 *hfsplus_compose_lookup(u16 *p, u16 cc) { int i, s, e; s = 1; e = p[1]; if (!e || cc < p[s * 2] || cc > p[e * 2]) return NULL; do { i = (s + e) / 2; if (cc > p[i * 2]) s = i + 1; else if (cc < p[i * 2]) e = i - 1; else return hfsplus_compose_table + p[i * 2 + 1]; } while (s <= e); return NULL; } int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, char *astr, int *len_p) { const hfsplus_unichr *ip; struct nls_table *nls = HFSPLUS_SB(sb)->nls; u8 *op; u16 cc, c0, c1; u16 *ce1, *ce2; int i, len, ustrlen, res, compose; op = astr; ip = ustr->unicode; ustrlen = be16_to_cpu(ustr->length); len = *len_p; ce1 = NULL; compose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags); while (ustrlen > 0) { c0 = be16_to_cpu(*ip++); ustrlen--; /* search for single decomposed char */ if (likely(compose)) ce1 = hfsplus_compose_lookup(hfsplus_compose_table, c0); if (ce1) cc = ce1[0]; else cc = 0; if (cc) { /* start of a possibly decomposed Hangul char */ if (cc != 0xffff) goto done; if (!ustrlen) goto same; c1 = be16_to_cpu(*ip) - Hangul_VBase; if (c1 < Hangul_VCount) { /* compose the Hangul char */ cc = (c0 - Hangul_LBase) * Hangul_VCount; cc = (cc + c1) * Hangul_TCount; cc += Hangul_SBase; ip++; ustrlen--; if (!ustrlen) goto done; c1 = be16_to_cpu(*ip) - Hangul_TBase; if (c1 > 0 && c1 < Hangul_TCount) { cc += c1; ip++; ustrlen--; } goto done; } } while (1) { /* main loop for common case of not composed chars */ if (!ustrlen) goto same; c1 = be16_to_cpu(*ip); if (likely(compose)) ce1 = hfsplus_compose_lookup( hfsplus_compose_table, c1); if (ce1) break; switch (c0) { case 0: c0 = 0x2400; break; case '/': c0 = ':'; break; } res = nls->uni2char(c0, op, len); if (res < 0) { if (res == -ENAMETOOLONG) goto out; *op = '?'; res = 1; } op += res; len -= res; c0 = c1; ip++; ustrlen--; } ce2 = hfsplus_compose_lookup(ce1, c0); if (ce2) { i = 1; while (i < ustrlen) { ce1 = hfsplus_compose_lookup(ce2, be16_to_cpu(ip[i])); if (!ce1) break; i++; ce2 = ce1; } cc = ce2[0]; if (cc) { ip += i; ustrlen -= i; goto done; } } same: switch (c0) { case 0: cc = 0x2400; break; case '/': cc = ':'; break; default: cc = c0; } done: res = nls->uni2char(cc, op, len); if (res < 0) { if (res == -ENAMETOOLONG) goto out; *op = '?'; res = 1; } op += res; len -= res; } res = 0; out: *len_p = (char *)op - astr; return res; } /* * Convert one or more ASCII characters into a single unicode character. * Returns the number of ASCII characters corresponding to the unicode char. */ static inline int asc2unichar(struct super_block *sb, const char *astr, int len, wchar_t *uc) { int size = HFSPLUS_SB(sb)->nls->char2uni(astr, len, uc); if (size <= 0) { *uc = '?'; size = 1; } switch (*uc) { case 0x2400: *uc = 0; break; case ':': *uc = '/'; break; } return size; } /* Decomposes a non-Hangul unicode character. */ static u16 *hfsplus_decompose_nonhangul(wchar_t uc, int *size) { int off; off = hfsplus_decompose_table[(uc >> 12) & 0xf]; if (off == 0 || off == 0xffff) return NULL; off = hfsplus_decompose_table[off + ((uc >> 8) & 0xf)]; if (!off) return NULL; off = hfsplus_decompose_table[off + ((uc >> 4) & 0xf)]; if (!off) return NULL; off = hfsplus_decompose_table[off + (uc & 0xf)]; *size = off & 3; if (*size == 0) return NULL; return hfsplus_decompose_table + (off / 4); } /* * Try to decompose a unicode character as Hangul. Return 0 if @uc is not * precomposed Hangul, otherwise return the length of the decomposition. * * This function was adapted from sample code from the Unicode Standard * Annex #15: Unicode Normalization Forms, version 3.2.0. * * Copyright (C) 1991-2018 Unicode, Inc. All rights reserved. Distributed * under the Terms of Use in http://www.unicode.org/copyright.html. */ static int hfsplus_try_decompose_hangul(wchar_t uc, u16 *result) { int index; int l, v, t; index = uc - Hangul_SBase; if (index < 0 || index >= Hangul_SCount) return 0; l = Hangul_LBase + index / Hangul_NCount; v = Hangul_VBase + (index % Hangul_NCount) / Hangul_TCount; t = Hangul_TBase + index % Hangul_TCount; result[0] = l; result[1] = v; if (t != Hangul_TBase) { result[2] = t; return 3; } return 2; } /* Decomposes a single unicode character. */ static u16 *decompose_unichar(wchar_t uc, int *size, u16 *hangul_buffer) { u16 *result; /* Hangul is handled separately */ result = hangul_buffer; *size = hfsplus_try_decompose_hangul(uc, result); if (*size == 0) result = hfsplus_decompose_nonhangul(uc, size); return result; } int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr, int max_unistr_len, const char *astr, int len) { int size, dsize, decompose; u16 *dstr, outlen = 0; wchar_t c; u16 dhangul[3]; decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags); while (outlen < max_unistr_len && len > 0) { size = asc2unichar(sb, astr, len, &c); if (decompose) dstr = decompose_unichar(c, &dsize, dhangul); else dstr = NULL; if (dstr) { if (outlen + dsize > max_unistr_len) break; do { ustr->unicode[outlen++] = cpu_to_be16(*dstr++); } while (--dsize > 0); } else ustr->unicode[outlen++] = cpu_to_be16(c); astr += size; len -= size; } ustr->length = cpu_to_be16(outlen); if (len > 0) return -ENAMETOOLONG; return 0; } /* * Hash a string to an integer as appropriate for the HFS+ filesystem. * Composed unicode characters are decomposed and case-folding is performed * if the appropriate bits are (un)set on the superblock. */ int hfsplus_hash_dentry(const struct dentry *dentry, struct qstr *str) { struct super_block *sb = dentry->d_sb; const char *astr; const u16 *dstr; int casefold, decompose, size, len; unsigned long hash; wchar_t c; u16 c2; u16 dhangul[3]; casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags); decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags); hash = init_name_hash(dentry); astr = str->name; len = str->len; while (len > 0) { int dsize; size = asc2unichar(sb, astr, len, &c); astr += size; len -= size; if (decompose) dstr = decompose_unichar(c, &dsize, dhangul); else dstr = NULL; if (dstr) { do { c2 = *dstr++; if (casefold) c2 = case_fold(c2); if (!casefold || c2) hash = partial_name_hash(c2, hash); } while (--dsize > 0); } else { c2 = c; if (casefold) c2 = case_fold(c2); if (!casefold || c2) hash = partial_name_hash(c2, hash); } } str->hash = end_name_hash(hash); return 0; } /* * Compare strings with HFS+ filename ordering. * Composed unicode characters are decomposed and case-folding is performed * if the appropriate bits are (un)set on the superblock. */ int hfsplus_compare_dentry(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { struct super_block *sb = dentry->d_sb; int casefold, decompose, size; int dsize1, dsize2, len1, len2; const u16 *dstr1, *dstr2; const char *astr1, *astr2; u16 c1, c2; wchar_t c; u16 dhangul_1[3], dhangul_2[3]; casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags); decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags); astr1 = str; len1 = len; astr2 = name->name; len2 = name->len; dsize1 = dsize2 = 0; dstr1 = dstr2 = NULL; while (len1 > 0 && len2 > 0) { if (!dsize1) { size = asc2unichar(sb, astr1, len1, &c); astr1 += size; len1 -= size; if (decompose) dstr1 = decompose_unichar(c, &dsize1, dhangul_1); if (!decompose || !dstr1) { c1 = c; dstr1 = &c1; dsize1 = 1; } } if (!dsize2) { size = asc2unichar(sb, astr2, len2, &c); astr2 += size; len2 -= size; if (decompose) dstr2 = decompose_unichar(c, &dsize2, dhangul_2); if (!decompose || !dstr2) { c2 = c; dstr2 = &c2; dsize2 = 1; } } c1 = *dstr1; c2 = *dstr2; if (casefold) { c1 = case_fold(c1); if (!c1) { dstr1++; dsize1--; continue; } c2 = case_fold(c2); if (!c2) { dstr2++; dsize2--; continue; } } if (c1 < c2) return -1; else if (c1 > c2) return 1; dstr1++; dsize1--; dstr2++; dsize2--; } if (len1 < len2) return -1; if (len1 > len2) return 1; return 0; } |
| 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 | // SPDX-License-Identifier: GPL-2.0-only /* * Ram backed block device driver. * * Copyright (C) 2007 Nick Piggin * Copyright (C) 2007 Novell Inc. * * Parts derived from drivers/block/rd.c, and drivers/block/loop.c, copyright * of their respective owners. */ #include <linux/init.h> #include <linux/initrd.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/major.h> #include <linux/blkdev.h> #include <linux/bio.h> #include <linux/highmem.h> #include <linux/mutex.h> #include <linux/pagemap.h> #include <linux/xarray.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/debugfs.h> #include <linux/uaccess.h> /* * Each block ramdisk device has a xarray brd_pages of pages that stores * the pages containing the block device's contents. */ struct brd_device { int brd_number; struct gendisk *brd_disk; struct list_head brd_list; /* * Backing store of pages. This is the contents of the block device. */ struct xarray brd_pages; u64 brd_nr_pages; }; /* * Look up and return a brd's page for a given sector. */ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector) { return xa_load(&brd->brd_pages, sector >> PAGE_SECTORS_SHIFT); } /* * Insert a new page for a given sector, if one does not already exist. */ static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp) { pgoff_t idx = sector >> PAGE_SECTORS_SHIFT; struct page *page; int ret = 0; page = brd_lookup_page(brd, sector); if (page) return 0; page = alloc_page(gfp | __GFP_ZERO | __GFP_HIGHMEM); if (!page) return -ENOMEM; xa_lock(&brd->brd_pages); ret = __xa_insert(&brd->brd_pages, idx, page, gfp); if (!ret) brd->brd_nr_pages++; xa_unlock(&brd->brd_pages); if (ret < 0) { __free_page(page); if (ret == -EBUSY) ret = 0; } return ret; } /* * Free all backing store pages and xarray. This must only be called when * there are no other users of the device. */ static void brd_free_pages(struct brd_device *brd) { struct page *page; pgoff_t idx; xa_for_each(&brd->brd_pages, idx, page) { __free_page(page); cond_resched(); } xa_destroy(&brd->brd_pages); } /* * copy_to_brd_setup must be called before copy_to_brd. It may sleep. */ static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n, gfp_t gfp) { unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT; size_t copy; int ret; copy = min_t(size_t, n, PAGE_SIZE - offset); ret = brd_insert_page(brd, sector, gfp); if (ret) return ret; if (copy < n) { sector += copy >> SECTOR_SHIFT; ret = brd_insert_page(brd, sector, gfp); } return ret; } /* * Copy n bytes from src to the brd starting at sector. Does not sleep. */ static void copy_to_brd(struct brd_device *brd, const void *src, sector_t sector, size_t n) { struct page *page; void *dst; unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT; size_t copy; copy = min_t(size_t, n, PAGE_SIZE - offset); page = brd_lookup_page(brd, sector); BUG_ON(!page); dst = kmap_atomic(page); memcpy(dst + offset, src, copy); kunmap_atomic(dst); if (copy < n) { src += copy; sector += copy >> SECTOR_SHIFT; copy = n - copy; page = brd_lookup_page(brd, sector); BUG_ON(!page); dst = kmap_atomic(page); memcpy(dst, src, copy); kunmap_atomic(dst); } } /* * Copy n bytes to dst from the brd starting at sector. Does not sleep. */ static void copy_from_brd(void *dst, struct brd_device *brd, sector_t sector, size_t n) { struct page *page; void *src; unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT; size_t copy; copy = min_t(size_t, n, PAGE_SIZE - offset); page = brd_lookup_page(brd, sector); if (page) { src = kmap_atomic(page); memcpy(dst, src + offset, copy); kunmap_atomic(src); } else memset(dst, 0, copy); if (copy < n) { dst += copy; sector += copy >> SECTOR_SHIFT; copy = n - copy; page = brd_lookup_page(brd, sector); if (page) { src = kmap_atomic(page); memcpy(dst, src, copy); kunmap_atomic(src); } else memset(dst, 0, copy); } } /* * Process a single bvec of a bio. */ static int brd_do_bvec(struct brd_device *brd, struct page *page, unsigned int len, unsigned int off, blk_opf_t opf, sector_t sector) { void *mem; int err = 0; if (op_is_write(opf)) { /* * Must use NOIO because we don't want to recurse back into the * block or filesystem layers from page reclaim. */ gfp_t gfp = opf & REQ_NOWAIT ? GFP_NOWAIT : GFP_NOIO; err = copy_to_brd_setup(brd, sector, len, gfp); if (err) goto out; } mem = kmap_atomic(page); if (!op_is_write(opf)) { copy_from_brd(mem + off, brd, sector, len); flush_dcache_page(page); } else { flush_dcache_page(page); copy_to_brd(brd, mem + off, sector, len); } kunmap_atomic(mem); out: return err; } static void brd_do_discard(struct brd_device *brd, sector_t sector, u32 size) { sector_t aligned_sector = (sector + PAGE_SECTORS) & ~PAGE_SECTORS; struct page *page; size -= (aligned_sector - sector) * SECTOR_SIZE; xa_lock(&brd->brd_pages); while (size >= PAGE_SIZE && aligned_sector < rd_size * 2) { page = __xa_erase(&brd->brd_pages, aligned_sector >> PAGE_SECTORS_SHIFT); if (page) __free_page(page); aligned_sector += PAGE_SECTORS; size -= PAGE_SIZE; } xa_unlock(&brd->brd_pages); } static void brd_submit_bio(struct bio *bio) { struct brd_device *brd = bio->bi_bdev->bd_disk->private_data; sector_t sector = bio->bi_iter.bi_sector; struct bio_vec bvec; struct bvec_iter iter; if (unlikely(op_is_discard(bio->bi_opf))) { brd_do_discard(brd, sector, bio->bi_iter.bi_size); bio_endio(bio); return; } bio_for_each_segment(bvec, bio, iter) { unsigned int len = bvec.bv_len; int err; /* Don't support un-aligned buffer */ WARN_ON_ONCE((bvec.bv_offset & (SECTOR_SIZE - 1)) || (len & (SECTOR_SIZE - 1))); err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset, bio->bi_opf, sector); if (err) { if (err == -ENOMEM && bio->bi_opf & REQ_NOWAIT) { bio_wouldblock_error(bio); return; } bio_io_error(bio); return; } sector += len >> SECTOR_SHIFT; } bio_endio(bio); } static const struct block_device_operations brd_fops = { .owner = THIS_MODULE, .submit_bio = brd_submit_bio, }; /* * And now the modules code and kernel interface. */ static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT; module_param(rd_nr, int, 0444); MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices"); unsigned long rd_size = CONFIG_BLK_DEV_RAM_SIZE; module_param(rd_size, ulong, 0444); MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes."); static int max_part = 1; module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices"); MODULE_DESCRIPTION("Ram backed block device driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR); MODULE_ALIAS("rd"); #ifndef MODULE /* Legacy boot options - nonmodular */ static int __init ramdisk_size(char *str) { rd_size = simple_strtol(str, NULL, 0); return 1; } __setup("ramdisk_size=", ramdisk_size); #endif /* * The device scheme is derived from loop.c. Keep them in synch where possible * (should share code eventually). */ static LIST_HEAD(brd_devices); static struct dentry *brd_debugfs_dir; static int brd_alloc(int i) { struct brd_device *brd; struct gendisk *disk; char buf[DISK_NAME_LEN]; int err = -ENOMEM; struct queue_limits lim = { /* * This is so fdisk will align partitions on 4k, because of * direct_access API needing 4k alignment, returning a PFN * (This is only a problem on very small devices <= 4M, * otherwise fdisk will align on 1M. Regardless this call * is harmless) */ .physical_block_size = PAGE_SIZE, .max_hw_discard_sectors = UINT_MAX, .max_discard_segments = 1, .discard_granularity = PAGE_SIZE, .features = BLK_FEAT_SYNCHRONOUS | BLK_FEAT_NOWAIT, }; list_for_each_entry(brd, &brd_devices, brd_list) if (brd->brd_number == i) return -EEXIST; brd = kzalloc(sizeof(*brd), GFP_KERNEL); if (!brd) return -ENOMEM; brd->brd_number = i; list_add_tail(&brd->brd_list, &brd_devices); xa_init(&brd->brd_pages); snprintf(buf, DISK_NAME_LEN, "ram%d", i); if (!IS_ERR_OR_NULL(brd_debugfs_dir)) debugfs_create_u64(buf, 0444, brd_debugfs_dir, &brd->brd_nr_pages); disk = brd->brd_disk = blk_alloc_disk(&lim, NUMA_NO_NODE); if (IS_ERR(disk)) { err = PTR_ERR(disk); goto out_free_dev; } disk->major = RAMDISK_MAJOR; disk->first_minor = i * max_part; disk->minors = max_part; disk->fops = &brd_fops; disk->private_data = brd; strscpy(disk->disk_name, buf, DISK_NAME_LEN); set_capacity(disk, rd_size * 2); err = add_disk(disk); if (err) goto out_cleanup_disk; return 0; out_cleanup_disk: put_disk(disk); out_free_dev: list_del(&brd->brd_list); kfree(brd); return err; } static void brd_probe(dev_t dev) { brd_alloc(MINOR(dev) / max_part); } static void brd_cleanup(void) { struct brd_device *brd, *next; debugfs_remove_recursive(brd_debugfs_dir); list_for_each_entry_safe(brd, next, &brd_devices, brd_list) { del_gendisk(brd->brd_disk); put_disk(brd->brd_disk); brd_free_pages(brd); list_del(&brd->brd_list); kfree(brd); } } static inline void brd_check_and_reset_par(void) { if (unlikely(!max_part)) max_part = 1; /* * make sure 'max_part' can be divided exactly by (1U << MINORBITS), * otherwise, it is possiable to get same dev_t when adding partitions. */ if ((1U << MINORBITS) % max_part != 0) max_part = 1UL << fls(max_part); if (max_part > DISK_MAX_PARTS) { pr_info("brd: max_part can't be larger than %d, reset max_part = %d.\n", DISK_MAX_PARTS, DISK_MAX_PARTS); max_part = DISK_MAX_PARTS; } } static int __init brd_init(void) { int err, i; brd_check_and_reset_par(); brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL); for (i = 0; i < rd_nr; i++) { err = brd_alloc(i); if (err) goto out_free; } /* * brd module now has a feature to instantiate underlying device * structure on-demand, provided that there is an access dev node. * * (1) if rd_nr is specified, create that many upfront. else * it defaults to CONFIG_BLK_DEV_RAM_COUNT * (2) User can further extend brd devices by create dev node themselves * and have kernel automatically instantiate actual device * on-demand. Example: * mknod /path/devnod_name b 1 X # 1 is the rd major * fdisk -l /path/devnod_name * If (X / max_part) was not already created it will be created * dynamically. */ if (__register_blkdev(RAMDISK_MAJOR, "ramdisk", brd_probe)) { err = -EIO; goto out_free; } pr_info("brd: module loaded\n"); return 0; out_free: brd_cleanup(); pr_info("brd: module NOT loaded !!!\n"); return err; } static void __exit brd_exit(void) { unregister_blkdev(RAMDISK_MAJOR, "ramdisk"); brd_cleanup(); pr_info("brd: module unloaded\n"); } module_init(brd_init); module_exit(brd_exit); |
| 34 16 34 38 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 | /* * linux/fs/nls/nls_cp1250.c * * Charset cp1250 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x20ac, 0x0000, 0x201a, 0x0000, 0x201e, 0x2026, 0x2020, 0x2021, 0x0000, 0x2030, 0x0160, 0x2039, 0x015a, 0x0164, 0x017d, 0x0179, /* 0x90*/ 0x0000, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014, 0x0000, 0x2122, 0x0161, 0x203a, 0x015b, 0x0165, 0x017e, 0x017a, /* 0xa0*/ 0x00a0, 0x02c7, 0x02d8, 0x0141, 0x00a4, 0x0104, 0x00a6, 0x00a7, 0x00a8, 0x00a9, 0x015e, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x017b, /* 0xb0*/ 0x00b0, 0x00b1, 0x02db, 0x0142, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x0105, 0x015f, 0x00bb, 0x013d, 0x02dd, 0x013e, 0x017c, /* 0xc0*/ 0x0154, 0x00c1, 0x00c2, 0x0102, 0x00c4, 0x0139, 0x0106, 0x00c7, 0x010c, 0x00c9, 0x0118, 0x00cb, 0x011a, 0x00cd, 0x00ce, 0x010e, /* 0xd0*/ 0x0110, 0x0143, 0x0147, 0x00d3, 0x00d4, 0x0150, 0x00d6, 0x00d7, 0x0158, 0x016e, 0x00da, 0x0170, 0x00dc, 0x00dd, 0x0162, 0x00df, /* 0xe0*/ 0x0155, 0x00e1, 0x00e2, 0x0103, 0x00e4, 0x013a, 0x0107, 0x00e7, 0x010d, 0x00e9, 0x0119, 0x00eb, 0x011b, 0x00ed, 0x00ee, 0x010f, /* 0xf0*/ 0x0111, 0x0144, 0x0148, 0x00f3, 0x00f4, 0x0151, 0x00f6, 0x00f7, 0x0159, 0x016f, 0x00fa, 0x0171, 0x00fc, 0x00fd, 0x0163, 0x02d9, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0x00, 0xab, 0xac, 0xad, 0xae, 0x00, /* 0xa8-0xaf */ 0xb0, 0xb1, 0x00, 0x00, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0xc1, 0xc2, 0x00, 0xc4, 0x00, 0x00, 0xc7, /* 0xc0-0xc7 */ 0x00, 0xc9, 0x00, 0xcb, 0x00, 0xcd, 0xce, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0xd3, 0xd4, 0x00, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0x00, 0x00, 0xda, 0x00, 0xdc, 0xdd, 0x00, 0xdf, /* 0xd8-0xdf */ 0x00, 0xe1, 0xe2, 0x00, 0xe4, 0x00, 0x00, 0xe7, /* 0xe0-0xe7 */ 0x00, 0xe9, 0x00, 0xeb, 0x00, 0xed, 0xee, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0xf3, 0xf4, 0x00, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0x00, 0x00, 0xfa, 0x00, 0xfc, 0xfd, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0x00, 0x00, 0xc3, 0xe3, 0xa5, 0xb9, 0xc6, 0xe6, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xc8, 0xe8, 0xcf, 0xef, /* 0x08-0x0f */ 0xd0, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xca, 0xea, 0xcc, 0xec, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0xc5, 0xe5, 0x00, 0x00, 0xbc, 0xbe, 0x00, /* 0x38-0x3f */ 0x00, 0xa3, 0xb3, 0xd1, 0xf1, 0x00, 0x00, 0xd2, /* 0x40-0x47 */ 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xd5, 0xf5, 0x00, 0x00, 0xc0, 0xe0, 0x00, 0x00, /* 0x50-0x57 */ 0xd8, 0xf8, 0x8c, 0x9c, 0x00, 0x00, 0xaa, 0xba, /* 0x58-0x5f */ 0x8a, 0x9a, 0xde, 0xfe, 0x8d, 0x9d, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd9, 0xf9, /* 0x68-0x6f */ 0xdb, 0xfb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x8f, 0x9f, 0xaf, 0xbf, 0x8e, 0x9e, 0x00, /* 0x78-0x7f */ }; static const unsigned char page02[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xa1, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0xa2, 0xff, 0x00, 0xb2, 0x00, 0xbd, 0x00, 0x00, /* 0xd8-0xdf */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x96, 0x97, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x91, 0x92, 0x82, 0x00, 0x93, 0x94, 0x84, 0x00, /* 0x18-0x1f */ 0x86, 0x87, 0x95, 0x00, 0x00, 0x00, 0x85, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x89, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x8b, 0x9b, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ }; static const unsigned char page21[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x99, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, page02, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, page21, NULL, NULL, NULL, NULL, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x00, 0x82, 0x00, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x00, 0x89, 0x9a, 0x8b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x88-0x8f */ 0x00, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x00, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xb3, 0xa4, 0xb9, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xba, 0xab, 0xac, 0xad, 0xae, 0xbf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbe, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xc0-0xc7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xc8-0xcf */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xd7, /* 0xd0-0xd7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x00, 0x82, 0x00, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x00, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x00, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x00, 0x99, 0x8a, 0x9b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xa3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xa5, 0xaa, 0xbb, 0xbc, 0xbd, 0xbc, 0xaf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0x00, /* 0xd8-0xdf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xe0-0xe7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xe8-0xef */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xf7, /* 0xf0-0xf7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp1250", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp1250(void) { return register_nls(&table); } static void __exit exit_nls_cp1250(void) { unregister_nls(&table); } module_init(init_nls_cp1250) module_exit(exit_nls_cp1250) MODULE_DESCRIPTION("NLS Windows CP1250 (Slavic/Central European Languages)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 3 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Copyright (C) Alan Cox GW4PTS (alan@lxorguk.ukuu.org.uk) * Copyright (C) Jonathan Naylor G4KLX (g4klx@g4klx.demon.co.uk) * Copyright (C) Darryl Miles G7LED (dlm@g7led.demon.co.uk) * Copyright (C) Steven Whitehouse GW7RRM (stevew@acm.org) * Copyright (C) Joerg Reuter DL1BKE (jreuter@yaina.de) * Copyright (C) Hans-Joachim Hetscher DD8NE (dd8ne@bnv-bamberg.de) * Copyright (C) Hans Alblas PE1AYX (hans@esrac.ele.tue.nl) * Copyright (C) Frederic Rible F1OAT (frible@teaser.fr) */ #include <linux/capability.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/slab.h> #include <net/ax25.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/fcntl.h> #include <linux/termios.h> /* For TIOCINQ/OUTQ */ #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/sysctl.h> #include <linux/init.h> #include <linux/spinlock.h> #include <net/net_namespace.h> #include <net/tcp_states.h> #include <net/ip.h> #include <net/arp.h> HLIST_HEAD(ax25_list); DEFINE_SPINLOCK(ax25_list_lock); static const struct proto_ops ax25_proto_ops; static void ax25_free_sock(struct sock *sk) { ax25_cb_put(sk_to_ax25(sk)); } /* * Socket removal during an interrupt is now safe. */ static void ax25_cb_del(ax25_cb *ax25) { spin_lock_bh(&ax25_list_lock); if (!hlist_unhashed(&ax25->ax25_node)) { hlist_del_init(&ax25->ax25_node); ax25_cb_put(ax25); } spin_unlock_bh(&ax25_list_lock); } /* * Kill all bound sockets on a dropped device. */ static void ax25_kill_by_device(struct net_device *dev) { ax25_dev *ax25_dev; ax25_cb *s; struct sock *sk; if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) return; ax25_dev->device_up = false; spin_lock_bh(&ax25_list_lock); again: ax25_for_each(s, &ax25_list) { if (s->ax25_dev == ax25_dev) { sk = s->sk; if (!sk) { spin_unlock_bh(&ax25_list_lock); ax25_disconnect(s, ENETUNREACH); s->ax25_dev = NULL; ax25_cb_del(s); spin_lock_bh(&ax25_list_lock); goto again; } sock_hold(sk); spin_unlock_bh(&ax25_list_lock); lock_sock(sk); ax25_disconnect(s, ENETUNREACH); s->ax25_dev = NULL; if (sk->sk_socket) { netdev_put(ax25_dev->dev, &s->dev_tracker); ax25_dev_put(ax25_dev); } ax25_cb_del(s); release_sock(sk); spin_lock_bh(&ax25_list_lock); sock_put(sk); /* The entry could have been deleted from the * list meanwhile and thus the next pointer is * no longer valid. Play it safe and restart * the scan. Forward progress is ensured * because we set s->ax25_dev to NULL and we * are never passed a NULL 'dev' argument. */ goto again; } } spin_unlock_bh(&ax25_list_lock); } /* * Handle device status changes. */ static int ax25_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; /* Reject non AX.25 devices */ if (dev->type != ARPHRD_AX25) return NOTIFY_DONE; switch (event) { case NETDEV_UP: ax25_dev_device_up(dev); break; case NETDEV_DOWN: ax25_kill_by_device(dev); ax25_rt_device_down(dev); ax25_dev_device_down(dev); break; default: break; } return NOTIFY_DONE; } /* * Add a socket to the bound sockets list. */ void ax25_cb_add(ax25_cb *ax25) { spin_lock_bh(&ax25_list_lock); ax25_cb_hold(ax25); hlist_add_head(&ax25->ax25_node, &ax25_list); spin_unlock_bh(&ax25_list_lock); } /* * Find a socket that wants to accept the SABM we have just * received. */ struct sock *ax25_find_listener(ax25_address *addr, int digi, struct net_device *dev, int type) { ax25_cb *s; spin_lock(&ax25_list_lock); ax25_for_each(s, &ax25_list) { if ((s->iamdigi && !digi) || (!s->iamdigi && digi)) continue; if (s->sk && !ax25cmp(&s->source_addr, addr) && s->sk->sk_type == type && s->sk->sk_state == TCP_LISTEN) { /* If device is null we match any device */ if (s->ax25_dev == NULL || s->ax25_dev->dev == dev) { sock_hold(s->sk); spin_unlock(&ax25_list_lock); return s->sk; } } } spin_unlock(&ax25_list_lock); return NULL; } /* * Find an AX.25 socket given both ends. */ struct sock *ax25_get_socket(ax25_address *my_addr, ax25_address *dest_addr, int type) { struct sock *sk = NULL; ax25_cb *s; spin_lock(&ax25_list_lock); ax25_for_each(s, &ax25_list) { if (s->sk && !ax25cmp(&s->source_addr, my_addr) && !ax25cmp(&s->dest_addr, dest_addr) && s->sk->sk_type == type) { sk = s->sk; sock_hold(sk); break; } } spin_unlock(&ax25_list_lock); return sk; } /* * Find an AX.25 control block given both ends. It will only pick up * floating AX.25 control blocks or non Raw socket bound control blocks. */ ax25_cb *ax25_find_cb(const ax25_address *src_addr, ax25_address *dest_addr, ax25_digi *digi, struct net_device *dev) { ax25_cb *s; spin_lock_bh(&ax25_list_lock); ax25_for_each(s, &ax25_list) { if (s->sk && s->sk->sk_type != SOCK_SEQPACKET) continue; if (s->ax25_dev == NULL) continue; if (ax25cmp(&s->source_addr, src_addr) == 0 && ax25cmp(&s->dest_addr, dest_addr) == 0 && s->ax25_dev->dev == dev) { if (digi != NULL && digi->ndigi != 0) { if (s->digipeat == NULL) continue; if (ax25digicmp(s->digipeat, digi) != 0) continue; } else { if (s->digipeat != NULL && s->digipeat->ndigi != 0) continue; } ax25_cb_hold(s); spin_unlock_bh(&ax25_list_lock); return s; } } spin_unlock_bh(&ax25_list_lock); return NULL; } EXPORT_SYMBOL(ax25_find_cb); void ax25_send_to_raw(ax25_address *addr, struct sk_buff *skb, int proto) { ax25_cb *s; struct sk_buff *copy; spin_lock(&ax25_list_lock); ax25_for_each(s, &ax25_list) { if (s->sk != NULL && ax25cmp(&s->source_addr, addr) == 0 && s->sk->sk_type == SOCK_RAW && s->sk->sk_protocol == proto && s->ax25_dev->dev == skb->dev && atomic_read(&s->sk->sk_rmem_alloc) <= s->sk->sk_rcvbuf) { if ((copy = skb_clone(skb, GFP_ATOMIC)) == NULL) continue; if (sock_queue_rcv_skb(s->sk, copy) != 0) kfree_skb(copy); } } spin_unlock(&ax25_list_lock); } /* * Deferred destroy. */ void ax25_destroy_socket(ax25_cb *); /* * Handler for deferred kills. */ static void ax25_destroy_timer(struct timer_list *t) { ax25_cb *ax25 = from_timer(ax25, t, dtimer); struct sock *sk; sk=ax25->sk; bh_lock_sock(sk); sock_hold(sk); ax25_destroy_socket(ax25); bh_unlock_sock(sk); sock_put(sk); } /* * This is called from user mode and the timers. Thus it protects itself * against interrupt users but doesn't worry about being called during * work. Once it is removed from the queue no interrupt or bottom half * will touch it and we are (fairly 8-) ) safe. */ void ax25_destroy_socket(ax25_cb *ax25) { struct sk_buff *skb; ax25_cb_del(ax25); ax25_stop_heartbeat(ax25); ax25_stop_t1timer(ax25); ax25_stop_t2timer(ax25); ax25_stop_t3timer(ax25); ax25_stop_idletimer(ax25); ax25_clear_queues(ax25); /* Flush the queues */ if (ax25->sk != NULL) { while ((skb = skb_dequeue(&ax25->sk->sk_receive_queue)) != NULL) { if (skb->sk != ax25->sk) { /* A pending connection */ ax25_cb *sax25 = sk_to_ax25(skb->sk); /* Queue the unaccepted socket for death */ sock_orphan(skb->sk); /* 9A4GL: hack to release unaccepted sockets */ skb->sk->sk_state = TCP_LISTEN; ax25_start_heartbeat(sax25); sax25->state = AX25_STATE_0; } kfree_skb(skb); } skb_queue_purge(&ax25->sk->sk_write_queue); } if (ax25->sk != NULL) { if (sk_has_allocations(ax25->sk)) { /* Defer: outstanding buffers */ timer_setup(&ax25->dtimer, ax25_destroy_timer, 0); ax25->dtimer.expires = jiffies + 2 * HZ; add_timer(&ax25->dtimer); } else { struct sock *sk=ax25->sk; ax25->sk=NULL; sock_put(sk); } } else { ax25_cb_put(ax25); } } /* * dl1bke 960311: set parameters for existing AX.25 connections, * includes a KILL command to abort any connection. * VERY useful for debugging ;-) */ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) { struct ax25_ctl_struct ax25_ctl; ax25_digi digi; ax25_dev *ax25_dev; ax25_cb *ax25; unsigned int k; int ret = 0; if (copy_from_user(&ax25_ctl, arg, sizeof(ax25_ctl))) return -EFAULT; if (ax25_ctl.digi_count > AX25_MAX_DIGIS) return -EINVAL; if (ax25_ctl.arg > ULONG_MAX / HZ && ax25_ctl.cmd != AX25_KILL) return -EINVAL; ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr); if (!ax25_dev) return -ENODEV; digi.ndigi = ax25_ctl.digi_count; for (k = 0; k < digi.ndigi; k++) digi.calls[k] = ax25_ctl.digi_addr[k]; ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev); if (!ax25) { ax25_dev_put(ax25_dev); return -ENOTCONN; } switch (ax25_ctl.cmd) { case AX25_KILL: ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND); #ifdef CONFIG_AX25_DAMA_SLAVE if (ax25_dev->dama.slave && ax25->ax25_dev->values[AX25_VALUES_PROTOCOL] == AX25_PROTO_DAMA_SLAVE) ax25_dama_off(ax25); #endif ax25_disconnect(ax25, ENETRESET); break; case AX25_WINDOW: if (ax25->modulus == AX25_MODULUS) { if (ax25_ctl.arg < 1 || ax25_ctl.arg > 7) goto einval_put; } else { if (ax25_ctl.arg < 1 || ax25_ctl.arg > 63) goto einval_put; } ax25->window = ax25_ctl.arg; break; case AX25_T1: if (ax25_ctl.arg < 1 || ax25_ctl.arg > ULONG_MAX / HZ) goto einval_put; ax25->rtt = (ax25_ctl.arg * HZ) / 2; ax25->t1 = ax25_ctl.arg * HZ; break; case AX25_T2: if (ax25_ctl.arg < 1 || ax25_ctl.arg > ULONG_MAX / HZ) goto einval_put; ax25->t2 = ax25_ctl.arg * HZ; break; case AX25_N2: if (ax25_ctl.arg < 1 || ax25_ctl.arg > 31) goto einval_put; ax25->n2count = 0; ax25->n2 = ax25_ctl.arg; break; case AX25_T3: if (ax25_ctl.arg > ULONG_MAX / HZ) goto einval_put; ax25->t3 = ax25_ctl.arg * HZ; break; case AX25_IDLE: if (ax25_ctl.arg > ULONG_MAX / (60 * HZ)) goto einval_put; ax25->idle = ax25_ctl.arg * 60 * HZ; break; case AX25_PACLEN: if (ax25_ctl.arg < 16 || ax25_ctl.arg > 65535) goto einval_put; ax25->paclen = ax25_ctl.arg; break; default: goto einval_put; } out_put: ax25_dev_put(ax25_dev); ax25_cb_put(ax25); return ret; einval_put: ret = -EINVAL; goto out_put; } static void ax25_fillin_cb_from_dev(ax25_cb *ax25, ax25_dev *ax25_dev) { ax25->rtt = msecs_to_jiffies(ax25_dev->values[AX25_VALUES_T1]) / 2; ax25->t1 = msecs_to_jiffies(ax25_dev->values[AX25_VALUES_T1]); ax25->t2 = msecs_to_jiffies(ax25_dev->values[AX25_VALUES_T2]); ax25->t3 = msecs_to_jiffies(ax25_dev->values[AX25_VALUES_T3]); ax25->n2 = ax25_dev->values[AX25_VALUES_N2]; ax25->paclen = ax25_dev->values[AX25_VALUES_PACLEN]; ax25->idle = msecs_to_jiffies(ax25_dev->values[AX25_VALUES_IDLE]); ax25->backoff = ax25_dev->values[AX25_VALUES_BACKOFF]; if (ax25_dev->values[AX25_VALUES_AXDEFMODE]) { ax25->modulus = AX25_EMODULUS; ax25->window = ax25_dev->values[AX25_VALUES_EWINDOW]; } else { ax25->modulus = AX25_MODULUS; ax25->window = ax25_dev->values[AX25_VALUES_WINDOW]; } } /* * Fill in a created AX.25 created control block with the default * values for a particular device. */ void ax25_fillin_cb(ax25_cb *ax25, ax25_dev *ax25_dev) { ax25->ax25_dev = ax25_dev; if (ax25->ax25_dev != NULL) { ax25_fillin_cb_from_dev(ax25, ax25_dev); return; } /* * No device, use kernel / AX.25 spec default values */ ax25->rtt = msecs_to_jiffies(AX25_DEF_T1) / 2; ax25->t1 = msecs_to_jiffies(AX25_DEF_T1); ax25->t2 = msecs_to_jiffies(AX25_DEF_T2); ax25->t3 = msecs_to_jiffies(AX25_DEF_T3); ax25->n2 = AX25_DEF_N2; ax25->paclen = AX25_DEF_PACLEN; ax25->idle = msecs_to_jiffies(AX25_DEF_IDLE); ax25->backoff = AX25_DEF_BACKOFF; if (AX25_DEF_AXDEFMODE) { ax25->modulus = AX25_EMODULUS; ax25->window = AX25_DEF_EWINDOW; } else { ax25->modulus = AX25_MODULUS; ax25->window = AX25_DEF_WINDOW; } } /* * Create an empty AX.25 control block. */ ax25_cb *ax25_create_cb(void) { ax25_cb *ax25; if ((ax25 = kzalloc(sizeof(*ax25), GFP_ATOMIC)) == NULL) return NULL; refcount_set(&ax25->refcount, 1); skb_queue_head_init(&ax25->write_queue); skb_queue_head_init(&ax25->frag_queue); skb_queue_head_init(&ax25->ack_queue); skb_queue_head_init(&ax25->reseq_queue); ax25_setup_timers(ax25); ax25_fillin_cb(ax25, NULL); ax25->state = AX25_STATE_0; return ax25; } /* * Handling for system calls applied via the various interfaces to an * AX25 socket object */ static int ax25_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; ax25_cb *ax25; struct net_device *dev; char devname[IFNAMSIZ]; unsigned int opt; int res = 0; if (level != SOL_AX25) return -ENOPROTOOPT; if (optlen < sizeof(unsigned int)) return -EINVAL; if (copy_from_sockptr(&opt, optval, sizeof(unsigned int))) return -EFAULT; lock_sock(sk); ax25 = sk_to_ax25(sk); switch (optname) { case AX25_WINDOW: if (ax25->modulus == AX25_MODULUS) { if (opt < 1 || opt > 7) { res = -EINVAL; break; } } else { if (opt < 1 || opt > 63) { res = -EINVAL; break; } } ax25->window = opt; break; case AX25_T1: if (opt < 1 || opt > UINT_MAX / HZ) { res = -EINVAL; break; } ax25->rtt = (opt * HZ) >> 1; ax25->t1 = opt * HZ; break; case AX25_T2: if (opt < 1 || opt > UINT_MAX / HZ) { res = -EINVAL; break; } ax25->t2 = opt * HZ; break; case AX25_N2: if (opt < 1 || opt > 31) { res = -EINVAL; break; } ax25->n2 = opt; break; case AX25_T3: if (opt < 1 || opt > UINT_MAX / HZ) { res = -EINVAL; break; } ax25->t3 = opt * HZ; break; case AX25_IDLE: if (opt > UINT_MAX / (60 * HZ)) { res = -EINVAL; break; } ax25->idle = opt * 60 * HZ; break; case AX25_BACKOFF: if (opt > 2) { res = -EINVAL; break; } ax25->backoff = opt; break; case AX25_EXTSEQ: ax25->modulus = opt ? AX25_EMODULUS : AX25_MODULUS; break; case AX25_PIDINCL: ax25->pidincl = opt ? 1 : 0; break; case AX25_IAMDIGI: ax25->iamdigi = opt ? 1 : 0; break; case AX25_PACLEN: if (opt < 16 || opt > 65535) { res = -EINVAL; break; } ax25->paclen = opt; break; case SO_BINDTODEVICE: if (optlen > IFNAMSIZ - 1) optlen = IFNAMSIZ - 1; memset(devname, 0, sizeof(devname)); if (copy_from_sockptr(devname, optval, optlen)) { res = -EFAULT; break; } if (sk->sk_type == SOCK_SEQPACKET && (sock->state != SS_UNCONNECTED || sk->sk_state == TCP_LISTEN)) { res = -EADDRNOTAVAIL; break; } rtnl_lock(); dev = __dev_get_by_name(&init_net, devname); if (!dev) { rtnl_unlock(); res = -ENODEV; break; } ax25->ax25_dev = ax25_dev_ax25dev(dev); if (!ax25->ax25_dev) { rtnl_unlock(); res = -ENODEV; break; } ax25_fillin_cb(ax25, ax25->ax25_dev); rtnl_unlock(); break; default: res = -ENOPROTOOPT; } release_sock(sk); return res; } static int ax25_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; ax25_cb *ax25; struct ax25_dev *ax25_dev; char devname[IFNAMSIZ]; void *valptr; int val = 0; int maxlen, length; if (level != SOL_AX25) return -ENOPROTOOPT; if (get_user(maxlen, optlen)) return -EFAULT; if (maxlen < 1) return -EFAULT; valptr = &val; length = min_t(unsigned int, maxlen, sizeof(int)); lock_sock(sk); ax25 = sk_to_ax25(sk); switch (optname) { case AX25_WINDOW: val = ax25->window; break; case AX25_T1: val = ax25->t1 / HZ; break; case AX25_T2: val = ax25->t2 / HZ; break; case AX25_N2: val = ax25->n2; break; case AX25_T3: val = ax25->t3 / HZ; break; case AX25_IDLE: val = ax25->idle / (60 * HZ); break; case AX25_BACKOFF: val = ax25->backoff; break; case AX25_EXTSEQ: val = (ax25->modulus == AX25_EMODULUS); break; case AX25_PIDINCL: val = ax25->pidincl; break; case AX25_IAMDIGI: val = ax25->iamdigi; break; case AX25_PACLEN: val = ax25->paclen; break; case SO_BINDTODEVICE: ax25_dev = ax25->ax25_dev; if (ax25_dev != NULL && ax25_dev->dev != NULL) { strscpy(devname, ax25_dev->dev->name, sizeof(devname)); length = strlen(devname) + 1; } else { *devname = '\0'; length = 1; } valptr = devname; break; default: release_sock(sk); return -ENOPROTOOPT; } release_sock(sk); if (put_user(length, optlen)) return -EFAULT; return copy_to_user(optval, valptr, length) ? -EFAULT : 0; } static int ax25_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int res = 0; lock_sock(sk); if (sk->sk_type == SOCK_SEQPACKET && sk->sk_state != TCP_LISTEN) { sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; goto out; } res = -EOPNOTSUPP; out: release_sock(sk); return res; } /* * XXX: when creating ax25_sock we should update the .obj_size setting * below. */ static struct proto ax25_proto = { .name = "AX25", .owner = THIS_MODULE, .obj_size = sizeof(struct ax25_sock), }; static int ax25_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; ax25_cb *ax25; if (protocol < 0 || protocol > U8_MAX) return -EINVAL; if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; switch (sock->type) { case SOCK_DGRAM: if (protocol == 0 || protocol == PF_AX25) protocol = AX25_P_TEXT; break; case SOCK_SEQPACKET: switch (protocol) { case 0: case PF_AX25: /* For CLX */ protocol = AX25_P_TEXT; break; case AX25_P_SEGMENT: #ifdef CONFIG_INET case AX25_P_ARP: case AX25_P_IP: #endif #ifdef CONFIG_NETROM case AX25_P_NETROM: #endif #ifdef CONFIG_ROSE case AX25_P_ROSE: #endif return -ESOCKTNOSUPPORT; #ifdef CONFIG_NETROM_MODULE case AX25_P_NETROM: if (ax25_protocol_is_registered(AX25_P_NETROM)) return -ESOCKTNOSUPPORT; break; #endif #ifdef CONFIG_ROSE_MODULE case AX25_P_ROSE: if (ax25_protocol_is_registered(AX25_P_ROSE)) return -ESOCKTNOSUPPORT; break; #endif default: break; } break; case SOCK_RAW: if (!capable(CAP_NET_RAW)) return -EPERM; break; default: return -ESOCKTNOSUPPORT; } sk = sk_alloc(net, PF_AX25, GFP_ATOMIC, &ax25_proto, kern); if (sk == NULL) return -ENOMEM; ax25 = ax25_sk(sk)->cb = ax25_create_cb(); if (!ax25) { sk_free(sk); return -ENOMEM; } sock_init_data(sock, sk); sk->sk_destruct = ax25_free_sock; sock->ops = &ax25_proto_ops; sk->sk_protocol = protocol; ax25->sk = sk; return 0; } struct sock *ax25_make_new(struct sock *osk, struct ax25_dev *ax25_dev) { struct sock *sk; ax25_cb *ax25, *oax25; sk = sk_alloc(sock_net(osk), PF_AX25, GFP_ATOMIC, osk->sk_prot, 0); if (sk == NULL) return NULL; if ((ax25 = ax25_create_cb()) == NULL) { sk_free(sk); return NULL; } switch (osk->sk_type) { case SOCK_DGRAM: break; case SOCK_SEQPACKET: break; default: sk_free(sk); ax25_cb_put(ax25); return NULL; } sock_init_data(NULL, sk); sk->sk_type = osk->sk_type; sk->sk_priority = READ_ONCE(osk->sk_priority); sk->sk_protocol = osk->sk_protocol; sk->sk_rcvbuf = osk->sk_rcvbuf; sk->sk_sndbuf = osk->sk_sndbuf; sk->sk_state = TCP_ESTABLISHED; sock_copy_flags(sk, osk); oax25 = sk_to_ax25(osk); ax25->modulus = oax25->modulus; ax25->backoff = oax25->backoff; ax25->pidincl = oax25->pidincl; ax25->iamdigi = oax25->iamdigi; ax25->rtt = oax25->rtt; ax25->t1 = oax25->t1; ax25->t2 = oax25->t2; ax25->t3 = oax25->t3; ax25->n2 = oax25->n2; ax25->idle = oax25->idle; ax25->paclen = oax25->paclen; ax25->window = oax25->window; ax25->ax25_dev = ax25_dev; ax25->source_addr = oax25->source_addr; if (oax25->digipeat != NULL) { ax25->digipeat = kmemdup(oax25->digipeat, sizeof(ax25_digi), GFP_ATOMIC); if (ax25->digipeat == NULL) { sk_free(sk); ax25_cb_put(ax25); return NULL; } } ax25_sk(sk)->cb = ax25; sk->sk_destruct = ax25_free_sock; ax25->sk = sk; return sk; } static int ax25_release(struct socket *sock) { struct sock *sk = sock->sk; ax25_cb *ax25; ax25_dev *ax25_dev; if (sk == NULL) return 0; sock_hold(sk); lock_sock(sk); sock_orphan(sk); ax25 = sk_to_ax25(sk); ax25_dev = ax25->ax25_dev; if (sk->sk_type == SOCK_SEQPACKET) { switch (ax25->state) { case AX25_STATE_0: if (!sock_flag(ax25->sk, SOCK_DEAD)) { release_sock(sk); ax25_disconnect(ax25, 0); lock_sock(sk); } ax25_destroy_socket(ax25); break; case AX25_STATE_1: case AX25_STATE_2: ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND); release_sock(sk); ax25_disconnect(ax25, 0); lock_sock(sk); if (!sock_flag(ax25->sk, SOCK_DESTROY)) ax25_destroy_socket(ax25); break; case AX25_STATE_3: case AX25_STATE_4: ax25_clear_queues(ax25); ax25->n2count = 0; switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) { case AX25_PROTO_STD_SIMPLEX: case AX25_PROTO_STD_DUPLEX: ax25_send_control(ax25, AX25_DISC, AX25_POLLON, AX25_COMMAND); ax25_stop_t2timer(ax25); ax25_stop_t3timer(ax25); ax25_stop_idletimer(ax25); break; #ifdef CONFIG_AX25_DAMA_SLAVE case AX25_PROTO_DAMA_SLAVE: ax25_stop_t3timer(ax25); ax25_stop_idletimer(ax25); break; #endif } ax25_calculate_t1(ax25); ax25_start_t1timer(ax25); ax25->state = AX25_STATE_2; sk->sk_state = TCP_CLOSE; sk->sk_shutdown |= SEND_SHUTDOWN; sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DESTROY); break; default: break; } } else { sk->sk_state = TCP_CLOSE; sk->sk_shutdown |= SEND_SHUTDOWN; sk->sk_state_change(sk); ax25_destroy_socket(ax25); } if (ax25_dev) { if (!ax25_dev->device_up) { del_timer_sync(&ax25->timer); del_timer_sync(&ax25->t1timer); del_timer_sync(&ax25->t2timer); del_timer_sync(&ax25->t3timer); del_timer_sync(&ax25->idletimer); } netdev_put(ax25_dev->dev, &ax25->dev_tracker); ax25_dev_put(ax25_dev); } sock->sk = NULL; release_sock(sk); sock_put(sk); return 0; } /* * We support a funny extension here so you can (as root) give any callsign * digipeated via a local address as source. This hack is obsolete now * that we've implemented support for SO_BINDTODEVICE. It is however small * and trivially backward compatible. */ static int ax25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; struct full_sockaddr_ax25 *addr = (struct full_sockaddr_ax25 *)uaddr; ax25_dev *ax25_dev = NULL; ax25_uid_assoc *user; ax25_address call; ax25_cb *ax25; int err = 0; if (addr_len != sizeof(struct sockaddr_ax25) && addr_len != sizeof(struct full_sockaddr_ax25)) /* support for old structure may go away some time * ax25_bind(): uses old (6 digipeater) socket structure. */ if ((addr_len < sizeof(struct sockaddr_ax25) + sizeof(ax25_address) * 6) || (addr_len > sizeof(struct full_sockaddr_ax25))) return -EINVAL; if (addr->fsa_ax25.sax25_family != AF_AX25) return -EINVAL; user = ax25_findbyuid(current_euid()); if (user) { call = user->call; ax25_uid_put(user); } else { if (ax25_uid_policy && !capable(CAP_NET_ADMIN)) return -EACCES; call = addr->fsa_ax25.sax25_call; } lock_sock(sk); ax25 = sk_to_ax25(sk); if (!sock_flag(sk, SOCK_ZAPPED)) { err = -EINVAL; goto out; } ax25->source_addr = call; /* * User already set interface with SO_BINDTODEVICE */ if (ax25->ax25_dev != NULL) goto done; if (addr_len > sizeof(struct sockaddr_ax25) && addr->fsa_ax25.sax25_ndigis == 1) { if (ax25cmp(&addr->fsa_digipeater[0], &null_ax25_address) != 0 && (ax25_dev = ax25_addr_ax25dev(&addr->fsa_digipeater[0])) == NULL) { err = -EADDRNOTAVAIL; goto out; } } else { if ((ax25_dev = ax25_addr_ax25dev(&addr->fsa_ax25.sax25_call)) == NULL) { err = -EADDRNOTAVAIL; goto out; } } if (ax25_dev) { ax25_fillin_cb(ax25, ax25_dev); netdev_hold(ax25_dev->dev, &ax25->dev_tracker, GFP_ATOMIC); } done: ax25_cb_add(ax25); sock_reset_flag(sk, SOCK_ZAPPED); out: release_sock(sk); return err; } /* * FIXME: nonblock behaviour looks like it may have a bug. */ static int __must_check ax25_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; ax25_cb *ax25 = sk_to_ax25(sk), *ax25t; struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)uaddr; ax25_digi *digi = NULL; int ct = 0, err = 0; /* * some sanity checks. code further down depends on this */ if (addr_len == sizeof(struct sockaddr_ax25)) /* support for this will go away in early 2.5.x * ax25_connect(): uses obsolete socket structure */ ; else if (addr_len != sizeof(struct full_sockaddr_ax25)) /* support for old structure may go away some time * ax25_connect(): uses old (6 digipeater) socket structure. */ if ((addr_len < sizeof(struct sockaddr_ax25) + sizeof(ax25_address) * 6) || (addr_len > sizeof(struct full_sockaddr_ax25))) return -EINVAL; if (fsa->fsa_ax25.sax25_family != AF_AX25) return -EINVAL; lock_sock(sk); /* deal with restarts */ if (sock->state == SS_CONNECTING) { switch (sk->sk_state) { case TCP_SYN_SENT: /* still trying */ err = -EINPROGRESS; goto out_release; case TCP_ESTABLISHED: /* connection established */ sock->state = SS_CONNECTED; goto out_release; case TCP_CLOSE: /* connection refused */ sock->state = SS_UNCONNECTED; err = -ECONNREFUSED; goto out_release; } } if (sk->sk_state == TCP_ESTABLISHED && sk->sk_type == SOCK_SEQPACKET) { err = -EISCONN; /* No reconnect on a seqpacket socket */ goto out_release; } sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; kfree(ax25->digipeat); ax25->digipeat = NULL; /* * Handle digi-peaters to be used. */ if (addr_len > sizeof(struct sockaddr_ax25) && fsa->fsa_ax25.sax25_ndigis != 0) { /* Valid number of digipeaters ? */ if (fsa->fsa_ax25.sax25_ndigis < 1 || fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS || addr_len < sizeof(struct sockaddr_ax25) + sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) { err = -EINVAL; goto out_release; } if ((digi = kmalloc(sizeof(ax25_digi), GFP_KERNEL)) == NULL) { err = -ENOBUFS; goto out_release; } digi->ndigi = fsa->fsa_ax25.sax25_ndigis; digi->lastrepeat = -1; while (ct < fsa->fsa_ax25.sax25_ndigis) { if ((fsa->fsa_digipeater[ct].ax25_call[6] & AX25_HBIT) && ax25->iamdigi) { digi->repeated[ct] = 1; digi->lastrepeat = ct; } else { digi->repeated[ct] = 0; } digi->calls[ct] = fsa->fsa_digipeater[ct]; ct++; } } /* * Must bind first - autobinding in this may or may not work. If * the socket is already bound, check to see if the device has * been filled in, error if it hasn't. */ if (sock_flag(sk, SOCK_ZAPPED)) { /* check if we can remove this feature. It is broken. */ printk(KERN_WARNING "ax25_connect(): %s uses autobind, please contact jreuter@yaina.de\n", current->comm); if ((err = ax25_rt_autobind(ax25, &fsa->fsa_ax25.sax25_call)) < 0) { kfree(digi); goto out_release; } ax25_fillin_cb(ax25, ax25->ax25_dev); ax25_cb_add(ax25); } else { if (ax25->ax25_dev == NULL) { kfree(digi); err = -EHOSTUNREACH; goto out_release; } } if (sk->sk_type == SOCK_SEQPACKET && (ax25t=ax25_find_cb(&ax25->source_addr, &fsa->fsa_ax25.sax25_call, digi, ax25->ax25_dev->dev))) { kfree(digi); err = -EADDRINUSE; /* Already such a connection */ ax25_cb_put(ax25t); goto out_release; } ax25->dest_addr = fsa->fsa_ax25.sax25_call; ax25->digipeat = digi; /* First the easy one */ if (sk->sk_type != SOCK_SEQPACKET) { sock->state = SS_CONNECTED; sk->sk_state = TCP_ESTABLISHED; goto out_release; } /* Move to connecting socket, ax.25 lapb WAIT_UA.. */ sock->state = SS_CONNECTING; sk->sk_state = TCP_SYN_SENT; switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) { case AX25_PROTO_STD_SIMPLEX: case AX25_PROTO_STD_DUPLEX: ax25_std_establish_data_link(ax25); break; #ifdef CONFIG_AX25_DAMA_SLAVE case AX25_PROTO_DAMA_SLAVE: ax25->modulus = AX25_MODULUS; ax25->window = ax25->ax25_dev->values[AX25_VALUES_WINDOW]; if (ax25->ax25_dev->dama.slave) ax25_ds_establish_data_link(ax25); else ax25_std_establish_data_link(ax25); break; #endif } ax25->state = AX25_STATE_1; ax25_start_heartbeat(ax25); /* Now the loop */ if (sk->sk_state != TCP_ESTABLISHED && (flags & O_NONBLOCK)) { err = -EINPROGRESS; goto out_release; } if (sk->sk_state == TCP_SYN_SENT) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk->sk_state != TCP_SYN_SENT) break; if (!signal_pending(current)) { release_sock(sk); schedule(); lock_sock(sk); continue; } err = -ERESTARTSYS; break; } finish_wait(sk_sleep(sk), &wait); if (err) goto out_release; } if (sk->sk_state != TCP_ESTABLISHED) { /* Not in ABM, not in WAIT_UA -> failed */ sock->state = SS_UNCONNECTED; err = sock_error(sk); /* Always set at this point */ goto out_release; } sock->state = SS_CONNECTED; err = 0; out_release: release_sock(sk); return err; } static int ax25_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct sk_buff *skb; struct sock *newsk; ax25_dev *ax25_dev; DEFINE_WAIT(wait); struct sock *sk; ax25_cb *ax25; int err = 0; if (sock->state != SS_UNCONNECTED) return -EINVAL; if ((sk = sock->sk) == NULL) return -EINVAL; lock_sock(sk); if (sk->sk_type != SOCK_SEQPACKET) { err = -EOPNOTSUPP; goto out; } if (sk->sk_state != TCP_LISTEN) { err = -EINVAL; goto out; } /* * The read queue this time is holding sockets ready to use * hooked into the SABM we saved */ for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); skb = skb_dequeue(&sk->sk_receive_queue); if (skb) break; if (arg->flags & O_NONBLOCK) { err = -EWOULDBLOCK; break; } if (!signal_pending(current)) { release_sock(sk); schedule(); lock_sock(sk); continue; } err = -ERESTARTSYS; break; } finish_wait(sk_sleep(sk), &wait); if (err) goto out; newsk = skb->sk; sock_graft(newsk, newsock); /* Now attach up the new socket */ kfree_skb(skb); sk_acceptq_removed(sk); newsock->state = SS_CONNECTED; ax25 = sk_to_ax25(newsk); ax25_dev = ax25->ax25_dev; netdev_hold(ax25_dev->dev, &ax25->dev_tracker, GFP_ATOMIC); ax25_dev_hold(ax25_dev); out: release_sock(sk); return err; } static int ax25_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)uaddr; struct sock *sk = sock->sk; unsigned char ndigi, i; ax25_cb *ax25; int err = 0; memset(fsa, 0, sizeof(*fsa)); lock_sock(sk); ax25 = sk_to_ax25(sk); if (peer != 0) { if (sk->sk_state != TCP_ESTABLISHED) { err = -ENOTCONN; goto out; } fsa->fsa_ax25.sax25_family = AF_AX25; fsa->fsa_ax25.sax25_call = ax25->dest_addr; if (ax25->digipeat != NULL) { ndigi = ax25->digipeat->ndigi; fsa->fsa_ax25.sax25_ndigis = ndigi; for (i = 0; i < ndigi; i++) fsa->fsa_digipeater[i] = ax25->digipeat->calls[i]; } } else { fsa->fsa_ax25.sax25_family = AF_AX25; fsa->fsa_ax25.sax25_call = ax25->source_addr; fsa->fsa_ax25.sax25_ndigis = 1; if (ax25->ax25_dev != NULL) { memcpy(&fsa->fsa_digipeater[0], ax25->ax25_dev->dev->dev_addr, AX25_ADDR_LEN); } else { fsa->fsa_digipeater[0] = null_ax25_address; } } err = sizeof (struct full_sockaddr_ax25); out: release_sock(sk); return err; } static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_ax25 *, usax, msg->msg_name); struct sock *sk = sock->sk; struct sockaddr_ax25 sax; struct sk_buff *skb; ax25_digi dtmp, *dp; ax25_cb *ax25; size_t size; int lv, err, addr_len = msg->msg_namelen; if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_CMSG_COMPAT)) return -EINVAL; lock_sock(sk); ax25 = sk_to_ax25(sk); if (sock_flag(sk, SOCK_ZAPPED)) { err = -EADDRNOTAVAIL; goto out; } if (sk->sk_shutdown & SEND_SHUTDOWN) { send_sig(SIGPIPE, current, 0); err = -EPIPE; goto out; } if (ax25->ax25_dev == NULL) { err = -ENETUNREACH; goto out; } if (len > ax25->ax25_dev->dev->mtu) { err = -EMSGSIZE; goto out; } if (usax != NULL) { if (usax->sax25_family != AF_AX25) { err = -EINVAL; goto out; } if (addr_len == sizeof(struct sockaddr_ax25)) /* ax25_sendmsg(): uses obsolete socket structure */ ; else if (addr_len != sizeof(struct full_sockaddr_ax25)) /* support for old structure may go away some time * ax25_sendmsg(): uses old (6 digipeater) * socket structure. */ if ((addr_len < sizeof(struct sockaddr_ax25) + sizeof(ax25_address) * 6) || (addr_len > sizeof(struct full_sockaddr_ax25))) { err = -EINVAL; goto out; } if (addr_len > sizeof(struct sockaddr_ax25) && usax->sax25_ndigis != 0) { int ct = 0; struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax; /* Valid number of digipeaters ? */ if (usax->sax25_ndigis < 1 || usax->sax25_ndigis > AX25_MAX_DIGIS || addr_len < sizeof(struct sockaddr_ax25) + sizeof(ax25_address) * usax->sax25_ndigis) { err = -EINVAL; goto out; } dtmp.ndigi = usax->sax25_ndigis; while (ct < usax->sax25_ndigis) { dtmp.repeated[ct] = 0; dtmp.calls[ct] = fsa->fsa_digipeater[ct]; ct++; } dtmp.lastrepeat = 0; } sax = *usax; if (sk->sk_type == SOCK_SEQPACKET && ax25cmp(&ax25->dest_addr, &sax.sax25_call)) { err = -EISCONN; goto out; } if (usax->sax25_ndigis == 0) dp = NULL; else dp = &dtmp; } else { /* * FIXME: 1003.1g - if the socket is like this because * it has become closed (not started closed) and is VC * we ought to SIGPIPE, EPIPE */ if (sk->sk_state != TCP_ESTABLISHED) { err = -ENOTCONN; goto out; } sax.sax25_family = AF_AX25; sax.sax25_call = ax25->dest_addr; dp = ax25->digipeat; } /* Build a packet */ /* Assume the worst case */ size = len + ax25->ax25_dev->dev->hard_header_len; skb = sock_alloc_send_skb(sk, size, msg->msg_flags&MSG_DONTWAIT, &err); if (skb == NULL) goto out; skb_reserve(skb, size - len); /* User data follows immediately after the AX.25 data */ if (memcpy_from_msg(skb_put(skb, len), msg, len)) { err = -EFAULT; kfree_skb(skb); goto out; } skb_reset_network_header(skb); /* Add the PID if one is not supplied by the user in the skb */ if (!ax25->pidincl) *(u8 *)skb_push(skb, 1) = sk->sk_protocol; if (sk->sk_type == SOCK_SEQPACKET) { /* Connected mode sockets go via the LAPB machine */ if (sk->sk_state != TCP_ESTABLISHED) { kfree_skb(skb); err = -ENOTCONN; goto out; } /* Shove it onto the queue and kick */ ax25_output(ax25, ax25->paclen, skb); err = len; goto out; } skb_push(skb, 1 + ax25_addr_size(dp)); /* Building AX.25 Header */ /* Build an AX.25 header */ lv = ax25_addr_build(skb->data, &ax25->source_addr, &sax.sax25_call, dp, AX25_COMMAND, AX25_MODULUS); skb_set_transport_header(skb, lv); *skb_transport_header(skb) = AX25_UI; /* Datagram frames go straight out of the door as UI */ ax25_queue_xmit(skb, ax25->ax25_dev->dev); err = len; out: release_sock(sk); return err; } static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb, *last; struct sk_buff_head *sk_queue; int copied; int err = 0; int off = 0; long timeo; lock_sock(sk); /* * This works for seqpacket too. The receiver has ordered the * queue for us! We do one quick check first though */ if (sk->sk_type == SOCK_SEQPACKET && sk->sk_state != TCP_ESTABLISHED) { err = -ENOTCONN; goto out; } /* We need support for non-blocking reads. */ sk_queue = &sk->sk_receive_queue; skb = __skb_try_recv_datagram(sk, sk_queue, flags, &off, &err, &last); /* If no packet is available, release_sock(sk) and try again. */ if (!skb) { if (err != -EAGAIN) goto out; release_sock(sk); timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); while (timeo && !__skb_wait_for_more_packets(sk, sk_queue, &err, &timeo, last)) { skb = __skb_try_recv_datagram(sk, sk_queue, flags, &off, &err, &last); if (skb) break; if (err != -EAGAIN) goto done; } if (!skb) goto done; lock_sock(sk); } if (!sk_to_ax25(sk)->pidincl) skb_pull(skb, 1); /* Remove PID */ skb_reset_transport_header(skb); copied = skb->len; if (copied > size) { copied = size; msg->msg_flags |= MSG_TRUNC; } skb_copy_datagram_msg(skb, 0, msg, copied); if (msg->msg_name) { ax25_digi digi; ax25_address src; const unsigned char *mac = skb_mac_header(skb); DECLARE_SOCKADDR(struct sockaddr_ax25 *, sax, msg->msg_name); memset(sax, 0, sizeof(struct full_sockaddr_ax25)); ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL, &digi, NULL, NULL); sax->sax25_family = AF_AX25; /* We set this correctly, even though we may not let the application know the digi calls further down (because it did NOT ask to know them). This could get political... **/ sax->sax25_ndigis = digi.ndigi; sax->sax25_call = src; if (sax->sax25_ndigis != 0) { int ct; struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)sax; for (ct = 0; ct < digi.ndigi; ct++) fsa->fsa_digipeater[ct] = digi.calls[ct]; } msg->msg_namelen = sizeof(struct full_sockaddr_ax25); } skb_free_datagram(sk, skb); err = copied; out: release_sock(sk); done: return err; } static int ax25_shutdown(struct socket *sk, int how) { /* FIXME - generate DM and RNR states */ return -EOPNOTSUPP; } static int ax25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; void __user *argp = (void __user *)arg; int res = 0; lock_sock(sk); switch (cmd) { case TIOCOUTQ: { long amount; amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; res = put_user(amount, (int __user *)argp); break; } case TIOCINQ: { struct sk_buff *skb; long amount = 0L; /* These two are safe on a single CPU system as only user tasks fiddle here */ if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) amount = skb->len; res = put_user(amount, (int __user *) argp); break; } case SIOCAX25ADDUID: /* Add a uid to the uid/call map table */ case SIOCAX25DELUID: /* Delete a uid from the uid/call map table */ case SIOCAX25GETUID: { struct sockaddr_ax25 sax25; if (copy_from_user(&sax25, argp, sizeof(sax25))) { res = -EFAULT; break; } res = ax25_uid_ioctl(cmd, &sax25); break; } case SIOCAX25NOUID: { /* Set the default policy (default/bar) */ long amount; if (!capable(CAP_NET_ADMIN)) { res = -EPERM; break; } if (get_user(amount, (long __user *)argp)) { res = -EFAULT; break; } if (amount < 0 || amount > AX25_NOUID_BLOCK) { res = -EINVAL; break; } ax25_uid_policy = amount; res = 0; break; } case SIOCADDRT: case SIOCDELRT: case SIOCAX25OPTRT: if (!capable(CAP_NET_ADMIN)) { res = -EPERM; break; } res = ax25_rt_ioctl(cmd, argp); break; case SIOCAX25CTLCON: if (!capable(CAP_NET_ADMIN)) { res = -EPERM; break; } res = ax25_ctl_ioctl(cmd, argp); break; case SIOCAX25GETINFO: case SIOCAX25GETINFOOLD: { ax25_cb *ax25 = sk_to_ax25(sk); struct ax25_info_struct ax25_info; ax25_info.t1 = ax25->t1 / HZ; ax25_info.t2 = ax25->t2 / HZ; ax25_info.t3 = ax25->t3 / HZ; ax25_info.idle = ax25->idle / (60 * HZ); ax25_info.n2 = ax25->n2; ax25_info.t1timer = ax25_display_timer(&ax25->t1timer) / HZ; ax25_info.t2timer = ax25_display_timer(&ax25->t2timer) / HZ; ax25_info.t3timer = ax25_display_timer(&ax25->t3timer) / HZ; ax25_info.idletimer = ax25_display_timer(&ax25->idletimer) / (60 * HZ); ax25_info.n2count = ax25->n2count; ax25_info.state = ax25->state; ax25_info.rcv_q = sk_rmem_alloc_get(sk); ax25_info.snd_q = sk_wmem_alloc_get(sk); ax25_info.vs = ax25->vs; ax25_info.vr = ax25->vr; ax25_info.va = ax25->va; ax25_info.vs_max = ax25->vs; /* reserved */ ax25_info.paclen = ax25->paclen; ax25_info.window = ax25->window; /* old structure? */ if (cmd == SIOCAX25GETINFOOLD) { static int warned = 0; if (!warned) { printk(KERN_INFO "%s uses old SIOCAX25GETINFO\n", current->comm); warned=1; } if (copy_to_user(argp, &ax25_info, sizeof(struct ax25_info_struct_deprecated))) { res = -EFAULT; break; } } else { if (copy_to_user(argp, &ax25_info, sizeof(struct ax25_info_struct))) { res = -EINVAL; break; } } res = 0; break; } case SIOCAX25ADDFWD: case SIOCAX25DELFWD: { struct ax25_fwd_struct ax25_fwd; if (!capable(CAP_NET_ADMIN)) { res = -EPERM; break; } if (copy_from_user(&ax25_fwd, argp, sizeof(ax25_fwd))) { res = -EFAULT; break; } res = ax25_fwd_ioctl(cmd, &ax25_fwd); break; } case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCGIFMETRIC: case SIOCSIFMETRIC: res = -EINVAL; break; default: res = -ENOIOCTLCMD; break; } release_sock(sk); return res; } #ifdef CONFIG_PROC_FS static void *ax25_info_start(struct seq_file *seq, loff_t *pos) __acquires(ax25_list_lock) { spin_lock_bh(&ax25_list_lock); return seq_hlist_start(&ax25_list, *pos); } static void *ax25_info_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_hlist_next(v, &ax25_list, pos); } static void ax25_info_stop(struct seq_file *seq, void *v) __releases(ax25_list_lock) { spin_unlock_bh(&ax25_list_lock); } static int ax25_info_show(struct seq_file *seq, void *v) { ax25_cb *ax25 = hlist_entry(v, struct ax25_cb, ax25_node); char buf[11]; int k; /* * New format: * magic dev src_addr dest_addr,digi1,digi2,.. st vs vr va t1 t1 t2 t2 t3 t3 idle idle n2 n2 rtt window paclen Snd-Q Rcv-Q inode */ seq_printf(seq, "%p %s %s%s ", ax25, ax25->ax25_dev == NULL? "???" : ax25->ax25_dev->dev->name, ax2asc(buf, &ax25->source_addr), ax25->iamdigi? "*":""); seq_printf(seq, "%s", ax2asc(buf, &ax25->dest_addr)); for (k=0; (ax25->digipeat != NULL) && (k < ax25->digipeat->ndigi); k++) { seq_printf(seq, ",%s%s", ax2asc(buf, &ax25->digipeat->calls[k]), ax25->digipeat->repeated[k]? "*":""); } seq_printf(seq, " %d %d %d %d %lu %lu %lu %lu %lu %lu %lu %lu %d %d %lu %d %d", ax25->state, ax25->vs, ax25->vr, ax25->va, ax25_display_timer(&ax25->t1timer) / HZ, ax25->t1 / HZ, ax25_display_timer(&ax25->t2timer) / HZ, ax25->t2 / HZ, ax25_display_timer(&ax25->t3timer) / HZ, ax25->t3 / HZ, ax25_display_timer(&ax25->idletimer) / (60 * HZ), ax25->idle / (60 * HZ), ax25->n2count, ax25->n2, ax25->rtt / HZ, ax25->window, ax25->paclen); if (ax25->sk != NULL) { seq_printf(seq, " %d %d %lu\n", sk_wmem_alloc_get(ax25->sk), sk_rmem_alloc_get(ax25->sk), sock_i_ino(ax25->sk)); } else { seq_puts(seq, " * * *\n"); } return 0; } static const struct seq_operations ax25_info_seqops = { .start = ax25_info_start, .next = ax25_info_next, .stop = ax25_info_stop, .show = ax25_info_show, }; #endif static const struct net_proto_family ax25_family_ops = { .family = PF_AX25, .create = ax25_create, .owner = THIS_MODULE, }; static const struct proto_ops ax25_proto_ops = { .family = PF_AX25, .owner = THIS_MODULE, .release = ax25_release, .bind = ax25_bind, .connect = ax25_connect, .socketpair = sock_no_socketpair, .accept = ax25_accept, .getname = ax25_getname, .poll = datagram_poll, .ioctl = ax25_ioctl, .gettstamp = sock_gettstamp, .listen = ax25_listen, .shutdown = ax25_shutdown, .setsockopt = ax25_setsockopt, .getsockopt = ax25_getsockopt, .sendmsg = ax25_sendmsg, .recvmsg = ax25_recvmsg, .mmap = sock_no_mmap, }; /* * Called by socket.c on kernel start up */ static struct packet_type ax25_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_AX25), .func = ax25_kiss_rcv, }; static struct notifier_block ax25_dev_notifier = { .notifier_call = ax25_device_event, }; static int __init ax25_init(void) { int rc = proto_register(&ax25_proto, 0); if (rc != 0) goto out; sock_register(&ax25_family_ops); dev_add_pack(&ax25_packet_type); register_netdevice_notifier(&ax25_dev_notifier); proc_create_seq("ax25_route", 0444, init_net.proc_net, &ax25_rt_seqops); proc_create_seq("ax25", 0444, init_net.proc_net, &ax25_info_seqops); proc_create_seq("ax25_calls", 0444, init_net.proc_net, &ax25_uid_seqops); out: return rc; } module_init(ax25_init); MODULE_AUTHOR("Jonathan Naylor G4KLX <g4klx@g4klx.demon.co.uk>"); MODULE_DESCRIPTION("The amateur radio AX.25 link layer protocol"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_AX25); static void __exit ax25_exit(void) { remove_proc_entry("ax25_route", init_net.proc_net); remove_proc_entry("ax25", init_net.proc_net); remove_proc_entry("ax25_calls", init_net.proc_net); unregister_netdevice_notifier(&ax25_dev_notifier); dev_remove_pack(&ax25_packet_type); sock_unregister(PF_AX25); proto_unregister(&ax25_proto); ax25_rt_free(); ax25_uid_free(); ax25_dev_free(); } module_exit(ax25_exit); |
| 226 226 226 55 55 55 197 5 197 98 122 76 69 35 32 27 47 6 67 71 7 21 21 165 15 158 2 158 71 38 33 11 9 2 125 1 3 4 122 1 15 69 67 5 11 33 3 31 3 11 20 31 4 2 10 13 8 1 20 26 2 1 1 1 19 6 1 18 6 1 1 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/catalog.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Handling of catalog records */ #include "hfsplus_fs.h" #include "hfsplus_raw.h" int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *k1, const hfsplus_btree_key *k2) { __be32 k1p, k2p; k1p = k1->cat.parent; k2p = k2->cat.parent; if (k1p != k2p) return be32_to_cpu(k1p) < be32_to_cpu(k2p) ? -1 : 1; return hfsplus_strcasecmp(&k1->cat.name, &k2->cat.name); } int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1, const hfsplus_btree_key *k2) { __be32 k1p, k2p; k1p = k1->cat.parent; k2p = k2->cat.parent; if (k1p != k2p) return be32_to_cpu(k1p) < be32_to_cpu(k2p) ? -1 : 1; return hfsplus_strcmp(&k1->cat.name, &k2->cat.name); } /* Generates key for catalog file/folders record. */ int hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key, u32 parent, const struct qstr *str) { int len, err; key->cat.parent = cpu_to_be32(parent); err = hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN, str->name, str->len); if (unlikely(err < 0)) return err; len = be16_to_cpu(key->cat.name.length); key->key_len = cpu_to_be16(6 + 2 * len); return 0; } /* Generates key for catalog thread record. */ void hfsplus_cat_build_key_with_cnid(struct super_block *sb, hfsplus_btree_key *key, u32 parent) { key->cat.parent = cpu_to_be32(parent); key->cat.name.length = 0; key->key_len = cpu_to_be16(6); } static void hfsplus_cat_build_key_uni(hfsplus_btree_key *key, u32 parent, struct hfsplus_unistr *name) { int ustrlen; ustrlen = be16_to_cpu(name->length); key->cat.parent = cpu_to_be32(parent); key->cat.name.length = cpu_to_be16(ustrlen); ustrlen *= 2; memcpy(key->cat.name.unicode, name->unicode, ustrlen); key->key_len = cpu_to_be16(6 + ustrlen); } void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms) { if (inode->i_flags & S_IMMUTABLE) perms->rootflags |= HFSPLUS_FLG_IMMUTABLE; else perms->rootflags &= ~HFSPLUS_FLG_IMMUTABLE; if (inode->i_flags & S_APPEND) perms->rootflags |= HFSPLUS_FLG_APPEND; else perms->rootflags &= ~HFSPLUS_FLG_APPEND; perms->userflags = HFSPLUS_I(inode)->userflags; perms->mode = cpu_to_be16(inode->i_mode); perms->owner = cpu_to_be32(i_uid_read(inode)); perms->group = cpu_to_be32(i_gid_read(inode)); if (S_ISREG(inode->i_mode)) perms->dev = cpu_to_be32(inode->i_nlink); else if (S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode)) perms->dev = cpu_to_be32(inode->i_rdev); else perms->dev = 0; } static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct inode *inode) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb); if (S_ISDIR(inode->i_mode)) { struct hfsplus_cat_folder *folder; folder = &entry->folder; memset(folder, 0, sizeof(*folder)); folder->type = cpu_to_be16(HFSPLUS_FOLDER); if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) folder->flags |= cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT); folder->id = cpu_to_be32(inode->i_ino); HFSPLUS_I(inode)->create_date = folder->create_date = folder->content_mod_date = folder->attribute_mod_date = folder->access_date = hfsp_now2mt(); hfsplus_cat_set_perms(inode, &folder->permissions); if (inode == sbi->hidden_dir) /* invisible and namelocked */ folder->user_info.frFlags = cpu_to_be16(0x5000); return sizeof(*folder); } else { struct hfsplus_cat_file *file; file = &entry->file; memset(file, 0, sizeof(*file)); file->type = cpu_to_be16(HFSPLUS_FILE); file->flags = cpu_to_be16(HFSPLUS_FILE_THREAD_EXISTS); file->id = cpu_to_be32(cnid); HFSPLUS_I(inode)->create_date = file->create_date = file->content_mod_date = file->attribute_mod_date = file->access_date = hfsp_now2mt(); if (cnid == inode->i_ino) { hfsplus_cat_set_perms(inode, &file->permissions); if (S_ISLNK(inode->i_mode)) { file->user_info.fdType = cpu_to_be32(HFSP_SYMLINK_TYPE); file->user_info.fdCreator = cpu_to_be32(HFSP_SYMLINK_CREATOR); } else { file->user_info.fdType = cpu_to_be32(sbi->type); file->user_info.fdCreator = cpu_to_be32(sbi->creator); } if (HFSPLUS_FLG_IMMUTABLE & (file->permissions.rootflags | file->permissions.userflags)) file->flags |= cpu_to_be16(HFSPLUS_FILE_LOCKED); } else { file->user_info.fdType = cpu_to_be32(HFSP_HARDLINK_TYPE); file->user_info.fdCreator = cpu_to_be32(HFSP_HFSPLUS_CREATOR); file->user_info.fdFlags = cpu_to_be16(0x100); file->create_date = HFSPLUS_I(sbi->hidden_dir)->create_date; file->permissions.dev = cpu_to_be32(HFSPLUS_I(inode)->linkid); } return sizeof(*file); } } static int hfsplus_fill_cat_thread(struct super_block *sb, hfsplus_cat_entry *entry, int type, u32 parentid, const struct qstr *str) { int err; entry->type = cpu_to_be16(type); entry->thread.reserved = 0; entry->thread.parentID = cpu_to_be32(parentid); err = hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN, str->name, str->len); if (unlikely(err < 0)) return err; return 10 + be16_to_cpu(entry->thread.nodeName.length) * 2; } /* Try to get a catalog entry for given catalog id */ int hfsplus_find_cat(struct super_block *sb, u32 cnid, struct hfs_find_data *fd) { hfsplus_cat_entry tmp; int err; u16 type; hfsplus_cat_build_key_with_cnid(sb, fd->search_key, cnid); err = hfs_brec_read(fd, &tmp, sizeof(hfsplus_cat_entry)); if (err) return err; type = be16_to_cpu(tmp.type); if (type != HFSPLUS_FOLDER_THREAD && type != HFSPLUS_FILE_THREAD) { pr_err("found bad thread record in catalog\n"); return -EIO; } if (be16_to_cpu(tmp.thread.nodeName.length) > 255) { pr_err("catalog name length corrupted\n"); return -EIO; } hfsplus_cat_build_key_uni(fd->search_key, be32_to_cpu(tmp.thread.parentID), &tmp.thread.nodeName); return hfs_brec_find(fd, hfs_find_rec_by_key); } static void hfsplus_subfolders_inc(struct inode *dir) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) { /* * Increment subfolder count. Note, the value is only meaningful * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set. */ HFSPLUS_I(dir)->subfolders++; } } static void hfsplus_subfolders_dec(struct inode *dir) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb); if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) { /* * Decrement subfolder count. Note, the value is only meaningful * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set. * * Check for zero. Some subfolders may have been created * by an implementation ignorant of this counter. */ if (HFSPLUS_I(dir)->subfolders) HFSPLUS_I(dir)->subfolders--; } } int hfsplus_create_cat(u32 cnid, struct inode *dir, const struct qstr *str, struct inode *inode) { struct super_block *sb = dir->i_sb; struct hfs_find_data fd; hfsplus_cat_entry entry; int entry_size; int err; hfs_dbg(CAT_MOD, "create_cat: %s,%u(%d)\n", str->name, cnid, inode->i_nlink); err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); if (err) return err; /* * Fail early and avoid ENOSPC during the btree operations. We may * have to split the root node at most once. */ err = hfs_bmap_reserve(fd.tree, 2 * fd.tree->depth); if (err) goto err2; hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid); entry_size = hfsplus_fill_cat_thread(sb, &entry, S_ISDIR(inode->i_mode) ? HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD, dir->i_ino, str); if (unlikely(entry_size < 0)) { err = entry_size; goto err2; } err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) err = -EEXIST; goto err2; } err = hfs_brec_insert(&fd, &entry, entry_size); if (err) goto err2; err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); if (unlikely(err)) goto err1; entry_size = hfsplus_cat_build_record(&entry, cnid, inode); err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err != -ENOENT) { /* panic? */ if (!err) err = -EEXIST; goto err1; } err = hfs_brec_insert(&fd, &entry, entry_size); if (err) goto err1; dir->i_size++; if (S_ISDIR(inode->i_mode)) hfsplus_subfolders_inc(dir); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY); hfs_find_exit(&fd); return 0; err1: hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid); if (!hfs_brec_find(&fd, hfs_find_rec_by_key)) hfs_brec_remove(&fd); err2: hfs_find_exit(&fd); return err; } int hfsplus_delete_cat(u32 cnid, struct inode *dir, const struct qstr *str) { struct super_block *sb = dir->i_sb; struct hfs_find_data fd; struct hfsplus_fork_raw fork; struct list_head *pos; int err, off; u16 type; hfs_dbg(CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid); err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); if (err) return err; /* * Fail early and avoid ENOSPC during the btree operations. We may * have to split the root node at most once. */ err = hfs_bmap_reserve(fd.tree, 2 * (int)fd.tree->depth - 2); if (err) goto out; if (!str) { int len; hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid); err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; off = fd.entryoffset + offsetof(struct hfsplus_cat_thread, nodeName); fd.search_key->cat.parent = cpu_to_be32(dir->i_ino); hfs_bnode_read(fd.bnode, &fd.search_key->cat.name.length, off, 2); len = be16_to_cpu(fd.search_key->cat.name.length) * 2; hfs_bnode_read(fd.bnode, &fd.search_key->cat.name.unicode, off + 2, len); fd.search_key->key_len = cpu_to_be16(6 + len); } else { err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); if (unlikely(err)) goto out; } err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; type = hfs_bnode_read_u16(fd.bnode, fd.entryoffset); if (type == HFSPLUS_FILE) { #if 0 off = fd.entryoffset + offsetof(hfsplus_cat_file, data_fork); hfs_bnode_read(fd.bnode, &fork, off, sizeof(fork)); hfsplus_free_fork(sb, cnid, &fork, HFSPLUS_TYPE_DATA); #endif off = fd.entryoffset + offsetof(struct hfsplus_cat_file, rsrc_fork); hfs_bnode_read(fd.bnode, &fork, off, sizeof(fork)); hfsplus_free_fork(sb, cnid, &fork, HFSPLUS_TYPE_RSRC); } /* we only need to take spinlock for exclusion with ->release() */ spin_lock(&HFSPLUS_I(dir)->open_dir_lock); list_for_each(pos, &HFSPLUS_I(dir)->open_dir_list) { struct hfsplus_readdir_data *rd = list_entry(pos, struct hfsplus_readdir_data, list); if (fd.tree->keycmp(fd.search_key, (void *)&rd->key) < 0) rd->file->f_pos--; } spin_unlock(&HFSPLUS_I(dir)->open_dir_lock); err = hfs_brec_remove(&fd); if (err) goto out; hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid); err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; err = hfs_brec_remove(&fd); if (err) goto out; dir->i_size--; if (type == HFSPLUS_FOLDER) hfsplus_subfolders_dec(dir); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY); if (type == HFSPLUS_FILE || type == HFSPLUS_FOLDER) { if (HFSPLUS_SB(sb)->attr_tree) hfsplus_delete_all_attrs(dir, cnid); } out: hfs_find_exit(&fd); return err; } int hfsplus_rename_cat(u32 cnid, struct inode *src_dir, const struct qstr *src_name, struct inode *dst_dir, const struct qstr *dst_name) { struct super_block *sb = src_dir->i_sb; struct hfs_find_data src_fd, dst_fd; hfsplus_cat_entry entry; int entry_size, type; int err; hfs_dbg(CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", cnid, src_dir->i_ino, src_name->name, dst_dir->i_ino, dst_name->name); err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &src_fd); if (err) return err; dst_fd = src_fd; /* * Fail early and avoid ENOSPC during the btree operations. We may * have to split the root node at most twice. */ err = hfs_bmap_reserve(src_fd.tree, 4 * (int)src_fd.tree->depth - 1); if (err) goto out; /* find the old dir entry and read the data */ err = hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); if (unlikely(err)) goto out; err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; if (src_fd.entrylength > sizeof(entry) || src_fd.entrylength < 0) { err = -EIO; goto out; } hfs_bnode_read(src_fd.bnode, &entry, src_fd.entryoffset, src_fd.entrylength); type = be16_to_cpu(entry.type); /* create new dir entry with the data from the old entry */ err = hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name); if (unlikely(err)) goto out; err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) err = -EEXIST; goto out; } err = hfs_brec_insert(&dst_fd, &entry, src_fd.entrylength); if (err) goto out; dst_dir->i_size++; if (type == HFSPLUS_FOLDER) hfsplus_subfolders_inc(dst_dir); inode_set_mtime_to_ts(dst_dir, inode_set_ctime_current(dst_dir)); /* finally remove the old entry */ err = hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); if (unlikely(err)) goto out; err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; err = hfs_brec_remove(&src_fd); if (err) goto out; src_dir->i_size--; if (type == HFSPLUS_FOLDER) hfsplus_subfolders_dec(src_dir); inode_set_mtime_to_ts(src_dir, inode_set_ctime_current(src_dir)); /* remove old thread entry */ hfsplus_cat_build_key_with_cnid(sb, src_fd.search_key, cnid); err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; type = hfs_bnode_read_u16(src_fd.bnode, src_fd.entryoffset); err = hfs_brec_remove(&src_fd); if (err) goto out; /* create new thread entry */ hfsplus_cat_build_key_with_cnid(sb, dst_fd.search_key, cnid); entry_size = hfsplus_fill_cat_thread(sb, &entry, type, dst_dir->i_ino, dst_name); if (unlikely(entry_size < 0)) { err = entry_size; goto out; } err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) err = -EEXIST; goto out; } err = hfs_brec_insert(&dst_fd, &entry, entry_size); hfsplus_mark_inode_dirty(dst_dir, HFSPLUS_I_CAT_DIRTY); hfsplus_mark_inode_dirty(src_dir, HFSPLUS_I_CAT_DIRTY); out: hfs_bnode_put(dst_fd.bnode); hfs_find_exit(&src_fd); return err; } |
| 2 1 1 1 1 3 3 3 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * Copyright (c) 2022-2024 Oracle. * All rights reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_shared.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_bmap_btree.h" #include "xfs_inode.h" #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_trans.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_attr.h" #include "xfs_ioctl.h" #include "xfs_parent.h" #include "xfs_handle.h" #include "xfs_health.h" #include "xfs_icache.h" #include "xfs_export.h" #include "xfs_xattr.h" #include "xfs_acl.h" #include <linux/namei.h> static inline size_t xfs_filehandle_fid_len(void) { struct xfs_handle *handle = NULL; return sizeof(struct xfs_fid) - sizeof(handle->ha_fid.fid_len); } static inline size_t xfs_filehandle_init( struct xfs_mount *mp, xfs_ino_t ino, uint32_t gen, struct xfs_handle *handle) { memcpy(&handle->ha_fsid, mp->m_fixedfsid, sizeof(struct xfs_fsid)); handle->ha_fid.fid_len = xfs_filehandle_fid_len(); handle->ha_fid.fid_pad = 0; handle->ha_fid.fid_gen = gen; handle->ha_fid.fid_ino = ino; return sizeof(struct xfs_handle); } static inline size_t xfs_fshandle_init( struct xfs_mount *mp, struct xfs_handle *handle) { memcpy(&handle->ha_fsid, mp->m_fixedfsid, sizeof(struct xfs_fsid)); memset(&handle->ha_fid, 0, sizeof(handle->ha_fid)); return sizeof(struct xfs_fsid); } /* * xfs_find_handle maps from userspace xfs_fsop_handlereq structure to * a file or fs handle. * * XFS_IOC_PATH_TO_FSHANDLE * returns fs handle for a mount point or path within that mount point * XFS_IOC_FD_TO_HANDLE * returns full handle for a FD opened in user space * XFS_IOC_PATH_TO_HANDLE * returns full handle for a path */ int xfs_find_handle( unsigned int cmd, xfs_fsop_handlereq_t *hreq) { int hsize; xfs_handle_t handle; struct inode *inode; struct fd f = {NULL}; struct path path; int error; struct xfs_inode *ip; if (cmd == XFS_IOC_FD_TO_HANDLE) { f = fdget(hreq->fd); if (!f.file) return -EBADF; inode = file_inode(f.file); } else { error = user_path_at(AT_FDCWD, hreq->path, 0, &path); if (error) return error; inode = d_inode(path.dentry); } ip = XFS_I(inode); /* * We can only generate handles for inodes residing on a XFS filesystem, * and only for regular files, directories or symbolic links. */ error = -EINVAL; if (inode->i_sb->s_magic != XFS_SB_MAGIC) goto out_put; error = -EBADF; if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode) && !S_ISLNK(inode->i_mode)) goto out_put; memcpy(&handle.ha_fsid, ip->i_mount->m_fixedfsid, sizeof(xfs_fsid_t)); if (cmd == XFS_IOC_PATH_TO_FSHANDLE) hsize = xfs_fshandle_init(ip->i_mount, &handle); else hsize = xfs_filehandle_init(ip->i_mount, ip->i_ino, inode->i_generation, &handle); error = -EFAULT; if (copy_to_user(hreq->ohandle, &handle, hsize) || copy_to_user(hreq->ohandlen, &hsize, sizeof(__s32))) goto out_put; error = 0; out_put: if (cmd == XFS_IOC_FD_TO_HANDLE) fdput(f); else path_put(&path); return error; } /* * No need to do permission checks on the various pathname components * as the handle operations are privileged. */ STATIC int xfs_handle_acceptable( void *context, struct dentry *dentry) { return 1; } /* Convert handle already copied to kernel space into a dentry. */ static struct dentry * xfs_khandle_to_dentry( struct file *file, struct xfs_handle *handle) { struct xfs_fid64 fid = { .ino = handle->ha_fid.fid_ino, .gen = handle->ha_fid.fid_gen, }; /* * Only allow handle opens under a directory. */ if (!S_ISDIR(file_inode(file)->i_mode)) return ERR_PTR(-ENOTDIR); if (handle->ha_fid.fid_len != xfs_filehandle_fid_len()) return ERR_PTR(-EINVAL); return exportfs_decode_fh(file->f_path.mnt, (struct fid *)&fid, 3, FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG, xfs_handle_acceptable, NULL); } /* Convert handle already copied to kernel space into an xfs_inode. */ static struct xfs_inode * xfs_khandle_to_inode( struct file *file, struct xfs_handle *handle) { struct xfs_inode *ip = XFS_I(file_inode(file)); struct xfs_mount *mp = ip->i_mount; struct inode *inode; if (!S_ISDIR(VFS_I(ip)->i_mode)) return ERR_PTR(-ENOTDIR); if (handle->ha_fid.fid_len != xfs_filehandle_fid_len()) return ERR_PTR(-EINVAL); inode = xfs_nfs_get_inode(mp->m_super, handle->ha_fid.fid_ino, handle->ha_fid.fid_gen); if (IS_ERR(inode)) return ERR_CAST(inode); return XFS_I(inode); } /* * Convert userspace handle data into a dentry. */ struct dentry * xfs_handle_to_dentry( struct file *parfilp, void __user *uhandle, u32 hlen) { xfs_handle_t handle; if (hlen != sizeof(xfs_handle_t)) return ERR_PTR(-EINVAL); if (copy_from_user(&handle, uhandle, hlen)) return ERR_PTR(-EFAULT); return xfs_khandle_to_dentry(parfilp, &handle); } STATIC struct dentry * xfs_handlereq_to_dentry( struct file *parfilp, xfs_fsop_handlereq_t *hreq) { return xfs_handle_to_dentry(parfilp, hreq->ihandle, hreq->ihandlen); } int xfs_open_by_handle( struct file *parfilp, xfs_fsop_handlereq_t *hreq) { const struct cred *cred = current_cred(); int error; int fd; int permflag; struct file *filp; struct inode *inode; struct dentry *dentry; fmode_t fmode; struct path path; if (!capable(CAP_SYS_ADMIN)) return -EPERM; dentry = xfs_handlereq_to_dentry(parfilp, hreq); if (IS_ERR(dentry)) return PTR_ERR(dentry); inode = d_inode(dentry); /* Restrict xfs_open_by_handle to directories & regular files. */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) { error = -EPERM; goto out_dput; } #if BITS_PER_LONG != 32 hreq->oflags |= O_LARGEFILE; #endif permflag = hreq->oflags; fmode = OPEN_FMODE(permflag); if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) && (fmode & FMODE_WRITE) && IS_APPEND(inode)) { error = -EPERM; goto out_dput; } if ((fmode & FMODE_WRITE) && IS_IMMUTABLE(inode)) { error = -EPERM; goto out_dput; } /* Can't write directories. */ if (S_ISDIR(inode->i_mode) && (fmode & FMODE_WRITE)) { error = -EISDIR; goto out_dput; } fd = get_unused_fd_flags(0); if (fd < 0) { error = fd; goto out_dput; } path.mnt = parfilp->f_path.mnt; path.dentry = dentry; filp = dentry_open(&path, hreq->oflags, cred); dput(dentry); if (IS_ERR(filp)) { put_unused_fd(fd); return PTR_ERR(filp); } if (S_ISREG(inode->i_mode)) { filp->f_flags |= O_NOATIME; filp->f_mode |= FMODE_NOCMTIME; } fd_install(fd, filp); return fd; out_dput: dput(dentry); return error; } int xfs_readlink_by_handle( struct file *parfilp, xfs_fsop_handlereq_t *hreq) { struct dentry *dentry; __u32 olen; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; dentry = xfs_handlereq_to_dentry(parfilp, hreq); if (IS_ERR(dentry)) return PTR_ERR(dentry); /* Restrict this handle operation to symlinks only. */ if (!d_is_symlink(dentry)) { error = -EINVAL; goto out_dput; } if (copy_from_user(&olen, hreq->ohandlen, sizeof(__u32))) { error = -EFAULT; goto out_dput; } error = vfs_readlink(dentry, hreq->ohandle, olen); out_dput: dput(dentry); return error; } /* * Format an attribute and copy it out to the user's buffer. * Take care to check values and protect against them changing later, * we may be reading them directly out of a user buffer. */ static void xfs_ioc_attr_put_listent( struct xfs_attr_list_context *context, int flags, unsigned char *name, int namelen, void *value, int valuelen) { struct xfs_attrlist *alist = context->buffer; struct xfs_attrlist_ent *aep; int arraytop; ASSERT(!context->seen_enough); ASSERT(context->count >= 0); ASSERT(context->count < (ATTR_MAX_VALUELEN/8)); ASSERT(context->firstu >= sizeof(*alist)); ASSERT(context->firstu <= context->bufsize); /* * Only list entries in the right namespace. */ if (context->attr_filter != (flags & XFS_ATTR_NSP_ONDISK_MASK)) return; arraytop = sizeof(*alist) + context->count * sizeof(alist->al_offset[0]); /* decrement by the actual bytes used by the attr */ context->firstu -= round_up(offsetof(struct xfs_attrlist_ent, a_name) + namelen + 1, sizeof(uint32_t)); if (context->firstu < arraytop) { trace_xfs_attr_list_full(context); alist->al_more = 1; context->seen_enough = 1; return; } aep = context->buffer + context->firstu; aep->a_valuelen = valuelen; memcpy(aep->a_name, name, namelen); aep->a_name[namelen] = 0; alist->al_offset[context->count++] = context->firstu; alist->al_count = context->count; trace_xfs_attr_list_add(context); } static unsigned int xfs_attr_filter( u32 ioc_flags) { if (ioc_flags & XFS_IOC_ATTR_ROOT) return XFS_ATTR_ROOT; if (ioc_flags & XFS_IOC_ATTR_SECURE) return XFS_ATTR_SECURE; return 0; } static inline enum xfs_attr_update xfs_xattr_flags( u32 ioc_flags, void *value) { if (!value) return XFS_ATTRUPDATE_REMOVE; if (ioc_flags & XFS_IOC_ATTR_CREATE) return XFS_ATTRUPDATE_CREATE; if (ioc_flags & XFS_IOC_ATTR_REPLACE) return XFS_ATTRUPDATE_REPLACE; return XFS_ATTRUPDATE_UPSERT; } int xfs_ioc_attr_list( struct xfs_inode *dp, void __user *ubuf, size_t bufsize, int flags, struct xfs_attrlist_cursor __user *ucursor) { struct xfs_attr_list_context context = { }; struct xfs_attrlist *alist; void *buffer; int error; if (bufsize < sizeof(struct xfs_attrlist) || bufsize > XFS_XATTR_LIST_MAX) return -EINVAL; /* * Reject flags, only allow namespaces. */ if (flags & ~(XFS_IOC_ATTR_ROOT | XFS_IOC_ATTR_SECURE)) return -EINVAL; if (flags == (XFS_IOC_ATTR_ROOT | XFS_IOC_ATTR_SECURE)) return -EINVAL; /* * Validate the cursor. */ if (copy_from_user(&context.cursor, ucursor, sizeof(context.cursor))) return -EFAULT; if (context.cursor.pad1 || context.cursor.pad2) return -EINVAL; if (!context.cursor.initted && (context.cursor.hashval || context.cursor.blkno || context.cursor.offset)) return -EINVAL; buffer = kvzalloc(bufsize, GFP_KERNEL); if (!buffer) return -ENOMEM; /* * Initialize the output buffer. */ context.dp = dp; context.resynch = 1; context.attr_filter = xfs_attr_filter(flags); context.buffer = buffer; context.bufsize = round_down(bufsize, sizeof(uint32_t)); context.firstu = context.bufsize; context.put_listent = xfs_ioc_attr_put_listent; alist = context.buffer; alist->al_count = 0; alist->al_more = 0; alist->al_offset[0] = context.bufsize; error = xfs_attr_list(&context); if (error) goto out_free; if (copy_to_user(ubuf, buffer, bufsize) || copy_to_user(ucursor, &context.cursor, sizeof(context.cursor))) error = -EFAULT; out_free: kvfree(buffer); return error; } int xfs_attrlist_by_handle( struct file *parfilp, struct xfs_fsop_attrlist_handlereq __user *p) { struct xfs_fsop_attrlist_handlereq al_hreq; struct dentry *dentry; int error = -ENOMEM; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (copy_from_user(&al_hreq, p, sizeof(al_hreq))) return -EFAULT; dentry = xfs_handlereq_to_dentry(parfilp, &al_hreq.hreq); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = xfs_ioc_attr_list(XFS_I(d_inode(dentry)), al_hreq.buffer, al_hreq.buflen, al_hreq.flags, &p->pos); dput(dentry); return error; } static int xfs_attrmulti_attr_get( struct inode *inode, unsigned char *name, unsigned char __user *ubuf, uint32_t *len, uint32_t flags) { struct xfs_da_args args = { .dp = XFS_I(inode), .attr_filter = xfs_attr_filter(flags), .name = name, .namelen = strlen(name), .valuelen = *len, }; int error; if (*len > XFS_XATTR_SIZE_MAX) return -EINVAL; error = xfs_attr_get(&args); if (error) goto out_kfree; *len = args.valuelen; if (copy_to_user(ubuf, args.value, args.valuelen)) error = -EFAULT; out_kfree: kvfree(args.value); return error; } static int xfs_attrmulti_attr_set( struct inode *inode, unsigned char *name, const unsigned char __user *ubuf, uint32_t len, uint32_t flags) { struct xfs_da_args args = { .dp = XFS_I(inode), .attr_filter = xfs_attr_filter(flags), .name = name, .namelen = strlen(name), }; int error; if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; if (ubuf) { if (len > XFS_XATTR_SIZE_MAX) return -EINVAL; args.value = memdup_user(ubuf, len); if (IS_ERR(args.value)) return PTR_ERR(args.value); args.valuelen = len; } error = xfs_attr_change(&args, xfs_xattr_flags(flags, args.value)); if (!error && (flags & XFS_IOC_ATTR_ROOT)) xfs_forget_acl(inode, name); kfree(args.value); return error; } int xfs_ioc_attrmulti_one( struct file *parfilp, struct inode *inode, uint32_t opcode, void __user *uname, void __user *value, uint32_t *len, uint32_t flags) { unsigned char *name; int error; if ((flags & XFS_IOC_ATTR_ROOT) && (flags & XFS_IOC_ATTR_SECURE)) return -EINVAL; name = strndup_user(uname, MAXNAMELEN); if (IS_ERR(name)) return PTR_ERR(name); switch (opcode) { case ATTR_OP_GET: error = xfs_attrmulti_attr_get(inode, name, value, len, flags); break; case ATTR_OP_REMOVE: value = NULL; *len = 0; fallthrough; case ATTR_OP_SET: error = mnt_want_write_file(parfilp); if (error) break; error = xfs_attrmulti_attr_set(inode, name, value, *len, flags); mnt_drop_write_file(parfilp); break; default: error = -EINVAL; break; } kfree(name); return error; } int xfs_attrmulti_by_handle( struct file *parfilp, void __user *arg) { int error; xfs_attr_multiop_t *ops; xfs_fsop_attrmulti_handlereq_t am_hreq; struct dentry *dentry; unsigned int i, size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (copy_from_user(&am_hreq, arg, sizeof(xfs_fsop_attrmulti_handlereq_t))) return -EFAULT; /* overflow check */ if (am_hreq.opcount >= INT_MAX / sizeof(xfs_attr_multiop_t)) return -E2BIG; dentry = xfs_handlereq_to_dentry(parfilp, &am_hreq.hreq); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = -E2BIG; size = am_hreq.opcount * sizeof(xfs_attr_multiop_t); if (!size || size > 16 * PAGE_SIZE) goto out_dput; ops = memdup_user(am_hreq.ops, size); if (IS_ERR(ops)) { error = PTR_ERR(ops); goto out_dput; } error = 0; for (i = 0; i < am_hreq.opcount; i++) { ops[i].am_error = xfs_ioc_attrmulti_one(parfilp, d_inode(dentry), ops[i].am_opcode, ops[i].am_attrname, ops[i].am_attrvalue, &ops[i].am_length, ops[i].am_flags); } if (copy_to_user(am_hreq.ops, ops, size)) error = -EFAULT; kfree(ops); out_dput: dput(dentry); return error; } struct xfs_getparents_ctx { struct xfs_attr_list_context context; struct xfs_getparents_by_handle gph; /* File to target */ struct xfs_inode *ip; /* Internal buffer where we format records */ void *krecords; /* Last record filled out */ struct xfs_getparents_rec *lastrec; unsigned int count; }; static inline unsigned int xfs_getparents_rec_sizeof( unsigned int namelen) { return round_up(sizeof(struct xfs_getparents_rec) + namelen + 1, sizeof(uint64_t)); } static void xfs_getparents_put_listent( struct xfs_attr_list_context *context, int flags, unsigned char *name, int namelen, void *value, int valuelen) { struct xfs_getparents_ctx *gpx = container_of(context, struct xfs_getparents_ctx, context); struct xfs_inode *ip = context->dp; struct xfs_mount *mp = ip->i_mount; struct xfs_getparents *gp = &gpx->gph.gph_request; struct xfs_getparents_rec *gpr = gpx->krecords + context->firstu; unsigned short reclen = xfs_getparents_rec_sizeof(namelen); xfs_ino_t ino; uint32_t gen; int error; if (!(flags & XFS_ATTR_PARENT)) return; error = xfs_parent_from_attr(mp, flags, name, namelen, value, valuelen, &ino, &gen); if (error) { xfs_inode_mark_sick(ip, XFS_SICK_INO_PARENT); context->seen_enough = -EFSCORRUPTED; return; } /* * We found a parent pointer, but we've filled up the buffer. Signal * to the caller that we did /not/ reach the end of the parent pointer * recordset. */ if (context->firstu > context->bufsize - reclen) { context->seen_enough = 1; return; } /* Format the parent pointer directly into the caller buffer. */ gpr->gpr_reclen = reclen; xfs_filehandle_init(mp, ino, gen, &gpr->gpr_parent); memcpy(gpr->gpr_name, name, namelen); gpr->gpr_name[namelen] = 0; trace_xfs_getparents_put_listent(ip, gp, context, gpr); context->firstu += reclen; gpx->count++; gpx->lastrec = gpr; } /* Expand the last record to fill the rest of the caller's buffer. */ static inline void xfs_getparents_expand_lastrec( struct xfs_getparents_ctx *gpx) { struct xfs_getparents *gp = &gpx->gph.gph_request; struct xfs_getparents_rec *gpr = gpx->lastrec; if (!gpx->lastrec) gpr = gpx->krecords; gpr->gpr_reclen = gp->gp_bufsize - ((void *)gpr - gpx->krecords); trace_xfs_getparents_expand_lastrec(gpx->ip, gp, &gpx->context, gpr); } /* Retrieve the parent pointers for a given inode. */ STATIC int xfs_getparents( struct xfs_getparents_ctx *gpx) { struct xfs_getparents *gp = &gpx->gph.gph_request; struct xfs_inode *ip = gpx->ip; struct xfs_mount *mp = ip->i_mount; size_t bufsize; int error; /* Check size of buffer requested by user */ if (gp->gp_bufsize > XFS_XATTR_LIST_MAX) return -ENOMEM; if (gp->gp_bufsize < xfs_getparents_rec_sizeof(1)) return -EINVAL; if (gp->gp_iflags & ~XFS_GETPARENTS_IFLAGS_ALL) return -EINVAL; if (gp->gp_reserved) return -EINVAL; bufsize = round_down(gp->gp_bufsize, sizeof(uint64_t)); gpx->krecords = kvzalloc(bufsize, GFP_KERNEL); if (!gpx->krecords) { bufsize = min(bufsize, PAGE_SIZE); gpx->krecords = kvzalloc(bufsize, GFP_KERNEL); if (!gpx->krecords) return -ENOMEM; } gpx->context.dp = ip; gpx->context.resynch = 1; gpx->context.put_listent = xfs_getparents_put_listent; gpx->context.bufsize = bufsize; /* firstu is used to track the bytes filled in the buffer */ gpx->context.firstu = 0; /* Copy the cursor provided by caller */ memcpy(&gpx->context.cursor, &gp->gp_cursor, sizeof(struct xfs_attrlist_cursor)); gpx->count = 0; gp->gp_oflags = 0; trace_xfs_getparents_begin(ip, gp, &gpx->context.cursor); error = xfs_attr_list(&gpx->context); if (error) goto out_free_buf; if (gpx->context.seen_enough < 0) { error = gpx->context.seen_enough; goto out_free_buf; } xfs_getparents_expand_lastrec(gpx); /* Update the caller with the current cursor position */ memcpy(&gp->gp_cursor, &gpx->context.cursor, sizeof(struct xfs_attrlist_cursor)); /* Is this the root directory? */ if (ip->i_ino == mp->m_sb.sb_rootino) gp->gp_oflags |= XFS_GETPARENTS_OFLAG_ROOT; if (gpx->context.seen_enough == 0) { /* * If we did not run out of buffer space, then we reached the * end of the pptr recordset, so set the DONE flag. */ gp->gp_oflags |= XFS_GETPARENTS_OFLAG_DONE; } else if (gpx->count == 0) { /* * If we ran out of buffer space before copying any parent * pointers at all, the caller's buffer was too short. Tell * userspace that, erm, the message is too long. */ error = -EMSGSIZE; goto out_free_buf; } trace_xfs_getparents_end(ip, gp, &gpx->context.cursor); ASSERT(gpx->context.firstu <= gpx->gph.gph_request.gp_bufsize); /* Copy the records to userspace. */ if (copy_to_user(u64_to_user_ptr(gpx->gph.gph_request.gp_buffer), gpx->krecords, gpx->context.firstu)) error = -EFAULT; out_free_buf: kvfree(gpx->krecords); gpx->krecords = NULL; return error; } /* Retrieve the parents of this file and pass them back to userspace. */ int xfs_ioc_getparents( struct file *file, struct xfs_getparents __user *ureq) { struct xfs_getparents_ctx gpx = { .ip = XFS_I(file_inode(file)), }; struct xfs_getparents *kreq = &gpx.gph.gph_request; struct xfs_mount *mp = gpx.ip->i_mount; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!xfs_has_parent(mp)) return -EOPNOTSUPP; if (copy_from_user(kreq, ureq, sizeof(*kreq))) return -EFAULT; error = xfs_getparents(&gpx); if (error) return error; if (copy_to_user(ureq, kreq, sizeof(*kreq))) return -EFAULT; return 0; } /* Retrieve the parents of this file handle and pass them back to userspace. */ int xfs_ioc_getparents_by_handle( struct file *file, struct xfs_getparents_by_handle __user *ureq) { struct xfs_getparents_ctx gpx = { }; struct xfs_inode *ip = XFS_I(file_inode(file)); struct xfs_mount *mp = ip->i_mount; struct xfs_getparents_by_handle *kreq = &gpx.gph; struct xfs_handle *handle = &kreq->gph_handle; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!xfs_has_parent(mp)) return -EOPNOTSUPP; if (copy_from_user(kreq, ureq, sizeof(*kreq))) return -EFAULT; /* * We don't use exportfs_decode_fh because it does too much work here. * If the handle refers to a directory, the exportfs code will walk * upwards through the directory tree to connect the dentries to the * root directory dentry. For GETPARENTS we don't care about that * because we're not actually going to open a file descriptor; we only * want to open an inode and read its parent pointers. * * Note that xfs_scrub uses GETPARENTS to log that it will try to fix a * corrupted file's metadata. For this usecase we would really rather * userspace single-step the path reconstruction to avoid loops or * other strange things if the directory tree is corrupt. */ gpx.ip = xfs_khandle_to_inode(file, handle); if (IS_ERR(gpx.ip)) return PTR_ERR(gpx.ip); error = xfs_getparents(&gpx); if (error) goto out_rele; if (copy_to_user(ureq, kreq, sizeof(*kreq))) error = -EFAULT; out_rele: xfs_irele(gpx.ip); return error; } |
| 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine (KVM) Hypervisor * * Copyright (C) 2006 Qumranet, Inc. * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> */ #include <kvm/iodev.h> #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/percpu.h> #include <linux/mm.h> #include <linux/miscdevice.h> #include <linux/vmalloc.h> #include <linux/reboot.h> #include <linux/debugfs.h> #include <linux/highmem.h> #include <linux/file.h> #include <linux/syscore_ops.h> #include <linux/cpu.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/sched/stat.h> #include <linux/cpumask.h> #include <linux/smp.h> #include <linux/anon_inodes.h> #include <linux/profile.h> #include <linux/kvm_para.h> #include <linux/pagemap.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/compat.h> #include <linux/srcu.h> #include <linux/hugetlb.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/bsearch.h> #include <linux/io.h> #include <linux/lockdep.h> #include <linux/kthread.h> #include <linux/suspend.h> #include <asm/processor.h> #include <asm/ioctl.h> #include <linux/uaccess.h> #include "coalesced_mmio.h" #include "async_pf.h" #include "kvm_mm.h" #include "vfio.h" #include <trace/events/ipi.h> #define CREATE_TRACE_POINTS #include <trace/events/kvm.h> #include <linux/kvm_dirty_ring.h> /* Worst case buffer size needed for holding an integer. */ #define ITOA_MAX_LEN 12 MODULE_AUTHOR("Qumranet"); MODULE_DESCRIPTION("Kernel-based Virtual Machine (KVM) Hypervisor"); MODULE_LICENSE("GPL"); /* Architectures should define their poll value according to the halt latency */ unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT; module_param(halt_poll_ns, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns); /* Default doubles per-vcpu halt_poll_ns. */ unsigned int halt_poll_ns_grow = 2; module_param(halt_poll_ns_grow, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_grow); /* The start value to grow halt_poll_ns from */ unsigned int halt_poll_ns_grow_start = 10000; /* 10us */ module_param(halt_poll_ns_grow_start, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start); /* Default halves per-vcpu halt_poll_ns. */ unsigned int halt_poll_ns_shrink = 2; module_param(halt_poll_ns_shrink, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_shrink); /* * Ordering of locks: * * kvm->lock --> kvm->slots_lock --> kvm->irq_lock */ DEFINE_MUTEX(kvm_lock); LIST_HEAD(vm_list); static struct kmem_cache *kvm_vcpu_cache; static __read_mostly struct preempt_ops kvm_preempt_ops; static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu); static struct dentry *kvm_debugfs_dir; static const struct file_operations stat_fops_per_vm; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); #ifdef CONFIG_KVM_COMPAT static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); #define KVM_COMPAT(c) .compat_ioctl = (c) #else /* * For architectures that don't implement a compat infrastructure, * adopt a double line of defense: * - Prevent a compat task from opening /dev/kvm * - If the open has been done by a 64bit task, and the KVM fd * passed to a compat task, let the ioctls fail. */ static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { return -EINVAL; } static int kvm_no_compat_open(struct inode *inode, struct file *file) { return is_compat_task() ? -ENODEV : 0; } #define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \ .open = kvm_no_compat_open #endif static int hardware_enable_all(void); static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); #define KVM_EVENT_CREATE_VM 0 #define KVM_EVENT_DESTROY_VM 1 static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); static unsigned long long kvm_createvm_count; static unsigned long long kvm_active_vms; static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask); __weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { } bool kvm_is_zone_device_page(struct page *page) { /* * The metadata used by is_zone_device_page() to determine whether or * not a page is ZONE_DEVICE is guaranteed to be valid if and only if * the device has been pinned, e.g. by get_user_pages(). WARN if the * page_count() is zero to help detect bad usage of this helper. */ if (WARN_ON_ONCE(!page_count(page))) return false; return is_zone_device_page(page); } /* * Returns a 'struct page' if the pfn is "valid" and backed by a refcounted * page, NULL otherwise. Note, the list of refcounted PG_reserved page types * is likely incomplete, it has been compiled purely through people wanting to * back guest with a certain type of memory and encountering issues. */ struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn) { struct page *page; if (!pfn_valid(pfn)) return NULL; page = pfn_to_page(pfn); if (!PageReserved(page)) return page; /* The ZERO_PAGE(s) is marked PG_reserved, but is refcounted. */ if (is_zero_pfn(pfn)) return page; /* * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting * perspective they are "normal" pages, albeit with slightly different * usage rules. */ if (kvm_is_zone_device_page(page)) return page; return NULL; } /* * Switches to specified vcpu, until a matching vcpu_put() */ void vcpu_load(struct kvm_vcpu *vcpu) { int cpu = get_cpu(); __this_cpu_write(kvm_running_vcpu, vcpu); preempt_notifier_register(&vcpu->preempt_notifier); kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); } EXPORT_SYMBOL_GPL(vcpu_load); void vcpu_put(struct kvm_vcpu *vcpu) { preempt_disable(); kvm_arch_vcpu_put(vcpu); preempt_notifier_unregister(&vcpu->preempt_notifier); __this_cpu_write(kvm_running_vcpu, NULL); preempt_enable(); } EXPORT_SYMBOL_GPL(vcpu_put); /* TODO: merge with kvm_arch_vcpu_should_kick */ static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req) { int mode = kvm_vcpu_exiting_guest_mode(vcpu); /* * We need to wait for the VCPU to reenable interrupts and get out of * READING_SHADOW_PAGE_TABLES mode. */ if (req & KVM_REQUEST_WAIT) return mode != OUTSIDE_GUEST_MODE; /* * Need to kick a running VCPU, but otherwise there is nothing to do. */ return mode == IN_GUEST_MODE; } static void ack_kick(void *_completed) { } static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait) { if (cpumask_empty(cpus)) return false; smp_call_function_many(cpus, ack_kick, NULL, wait); return true; } static void kvm_make_vcpu_request(struct kvm_vcpu *vcpu, unsigned int req, struct cpumask *tmp, int current_cpu) { int cpu; if (likely(!(req & KVM_REQUEST_NO_ACTION))) __kvm_make_request(req, vcpu); if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) return; /* * Note, the vCPU could get migrated to a different pCPU at any point * after kvm_request_needs_ipi(), which could result in sending an IPI * to the previous pCPU. But, that's OK because the purpose of the IPI * is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is * satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES * after this point is also OK, as the requirement is only that KVM wait * for vCPUs that were reading SPTEs _before_ any changes were * finalized. See kvm_vcpu_kick() for more details on handling requests. */ if (kvm_request_needs_ipi(vcpu, req)) { cpu = READ_ONCE(vcpu->cpu); if (cpu != -1 && cpu != current_cpu) __cpumask_set_cpu(cpu, tmp); } } bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap) { struct kvm_vcpu *vcpu; struct cpumask *cpus; int i, me; bool called; me = get_cpu(); cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); cpumask_clear(cpus); for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) { vcpu = kvm_get_vcpu(kvm, i); if (!vcpu) continue; kvm_make_vcpu_request(vcpu, req, cpus, me); } called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); return called; } bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) { struct kvm_vcpu *vcpu; struct cpumask *cpus; unsigned long i; bool called; int me; me = get_cpu(); cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); cpumask_clear(cpus); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_vcpu_request(vcpu, req, cpus, me); called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); return called; } EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); void kvm_flush_remote_tlbs(struct kvm *kvm) { ++kvm->stat.generic.remote_tlb_flush_requests; /* * We want to publish modifications to the page tables before reading * mode. Pairs with a memory barrier in arch-specific code. * - x86: smp_mb__after_srcu_read_unlock in vcpu_enter_guest * and smp_mb in walk_shadow_page_lockless_begin/end. * - powerpc: smp_mb in kvmppc_prepare_to_enter. * * There is already an smp_mb__after_atomic() before * kvm_make_all_cpus_request() reads vcpu->mode. We reuse that * barrier here. */ if (!kvm_arch_flush_remote_tlbs(kvm) || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) ++kvm->stat.generic.remote_tlb_flush; } EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages)) return; /* * Fall back to a flushing entire TLBs if the architecture range-based * TLB invalidation is unsupported or can't be performed for whatever * reason. */ kvm_flush_remote_tlbs(kvm); } void kvm_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot) { /* * All current use cases for flushing the TLBs for a specific memslot * are related to dirty logging, and many do the TLB flush out of * mmu_lock. The interaction between the various operations on memslot * must be serialized by slots_locks to ensure the TLB flush from one * operation is observed by any other operation on the same memslot. */ lockdep_assert_held(&kvm->slots_lock); kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages); } static void kvm_flush_shadow_all(struct kvm *kvm) { kvm_arch_flush_shadow_all(kvm); kvm_arch_guest_memory_reclaimed(kvm); } #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc, gfp_t gfp_flags) { void *page; gfp_flags |= mc->gfp_zero; if (mc->kmem_cache) return kmem_cache_alloc(mc->kmem_cache, gfp_flags); page = (void *)__get_free_page(gfp_flags); if (page && mc->init_value) memset64(page, mc->init_value, PAGE_SIZE / sizeof(u64)); return page; } int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min) { gfp_t gfp = mc->gfp_custom ? mc->gfp_custom : GFP_KERNEL_ACCOUNT; void *obj; if (mc->nobjs >= min) return 0; if (unlikely(!mc->objects)) { if (WARN_ON_ONCE(!capacity)) return -EIO; /* * Custom init values can be used only for page allocations, * and obviously conflict with __GFP_ZERO. */ if (WARN_ON_ONCE(mc->init_value && (mc->kmem_cache || mc->gfp_zero))) return -EIO; mc->objects = kvmalloc_array(capacity, sizeof(void *), gfp); if (!mc->objects) return -ENOMEM; mc->capacity = capacity; } /* It is illegal to request a different capacity across topups. */ if (WARN_ON_ONCE(mc->capacity != capacity)) return -EIO; while (mc->nobjs < mc->capacity) { obj = mmu_memory_cache_alloc_obj(mc, gfp); if (!obj) return mc->nobjs >= min ? 0 : -ENOMEM; mc->objects[mc->nobjs++] = obj; } return 0; } int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min) { return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min); } int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc) { return mc->nobjs; } void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) { while (mc->nobjs) { if (mc->kmem_cache) kmem_cache_free(mc->kmem_cache, mc->objects[--mc->nobjs]); else free_page((unsigned long)mc->objects[--mc->nobjs]); } kvfree(mc->objects); mc->objects = NULL; mc->capacity = 0; } void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) { void *p; if (WARN_ON(!mc->nobjs)) p = mmu_memory_cache_alloc_obj(mc, GFP_ATOMIC | __GFP_ACCOUNT); else p = mc->objects[--mc->nobjs]; BUG_ON(!p); return p; } #endif static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) { mutex_init(&vcpu->mutex); vcpu->cpu = -1; vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; #ifndef __KVM_HAVE_ARCH_WQP rcuwait_init(&vcpu->wait); #endif kvm_async_pf_vcpu_init(vcpu); kvm_vcpu_set_in_spin_loop(vcpu, false); kvm_vcpu_set_dy_eligible(vcpu, false); vcpu->preempted = false; vcpu->ready = false; preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); vcpu->last_used_slot = NULL; /* Fill the stats id string for the vcpu */ snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d", task_pid_nr(current), id); } static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { kvm_arch_vcpu_destroy(vcpu); kvm_dirty_ring_free(&vcpu->dirty_ring); /* * No need for rcu_read_lock as VCPU_RUN is the only place that changes * the vcpu->pid pointer, and at destruction time all file descriptors * are already gone. */ put_pid(rcu_dereference_protected(vcpu->pid, 1)); free_page((unsigned long)vcpu->run); kmem_cache_free(kvm_vcpu_cache, vcpu); } void kvm_destroy_vcpus(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { kvm_vcpu_destroy(vcpu); xa_erase(&kvm->vcpu_array, i); } atomic_set(&kvm->online_vcpus, 0); } EXPORT_SYMBOL_GPL(kvm_destroy_vcpus); #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) { return container_of(mn, struct kvm, mmu_notifier); } typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); typedef void (*on_lock_fn_t)(struct kvm *kvm); struct kvm_mmu_notifier_range { /* * 64-bit addresses, as KVM notifiers can operate on host virtual * addresses (unsigned long) and guest physical addresses (64-bit). */ u64 start; u64 end; union kvm_mmu_notifier_arg arg; gfn_handler_t handler; on_lock_fn_t on_lock; bool flush_on_ret; bool may_block; }; /* * The inner-most helper returns a tuple containing the return value from the * arch- and action-specific handler, plus a flag indicating whether or not at * least one memslot was found, i.e. if the handler found guest memory. * * Note, most notifiers are averse to booleans, so even though KVM tracks the * return from arch code as a bool, outer helpers will cast it to an int. :-( */ typedef struct kvm_mmu_notifier_return { bool ret; bool found_memslot; } kvm_mn_ret_t; /* * Use a dedicated stub instead of NULL to indicate that there is no callback * function/handler. The compiler technically can't guarantee that a real * function will have a non-zero address, and so it will generate code to * check for !NULL, whereas comparing against a stub will be elided at compile * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9). */ static void kvm_null_fn(void) { } #define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn) /* Iterate over each memslot intersecting [start, last] (inclusive) range */ #define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \ for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \ node; \ node = interval_tree_iter_next(node, start, last)) \ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm, const struct kvm_mmu_notifier_range *range) { struct kvm_mmu_notifier_return r = { .ret = false, .found_memslot = false, }; struct kvm_gfn_range gfn_range; struct kvm_memory_slot *slot; struct kvm_memslots *slots; int i, idx; if (WARN_ON_ONCE(range->end <= range->start)) return r; /* A null handler is allowed if and only if on_lock() is provided. */ if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) && IS_KVM_NULL_FN(range->handler))) return r; idx = srcu_read_lock(&kvm->srcu); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { struct interval_tree_node *node; slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_hva_range(node, slots, range->start, range->end - 1) { unsigned long hva_start, hva_end; slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]); hva_start = max_t(unsigned long, range->start, slot->userspace_addr); hva_end = min_t(unsigned long, range->end, slot->userspace_addr + (slot->npages << PAGE_SHIFT)); /* * To optimize for the likely case where the address * range is covered by zero or one memslots, don't * bother making these conditional (to avoid writes on * the second or later invocation of the handler). */ gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; /* * {gfn(page) | page intersects with [hva_start, hva_end)} = * {gfn_start, gfn_start+1, ..., gfn_end-1}. */ gfn_range.start = hva_to_gfn_memslot(hva_start, slot); gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot); gfn_range.slot = slot; if (!r.found_memslot) { r.found_memslot = true; KVM_MMU_LOCK(kvm); if (!IS_KVM_NULL_FN(range->on_lock)) range->on_lock(kvm); if (IS_KVM_NULL_FN(range->handler)) goto mmu_unlock; } r.ret |= range->handler(kvm, &gfn_range); } } if (range->flush_on_ret && r.ret) kvm_flush_remote_tlbs(kvm); mmu_unlock: if (r.found_memslot) KVM_MMU_UNLOCK(kvm); srcu_read_unlock(&kvm->srcu, idx); return r; } static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn, unsigned long start, unsigned long end, gfn_handler_t handler) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range range = { .start = start, .end = end, .handler = handler, .on_lock = (void *)kvm_null_fn, .flush_on_ret = true, .may_block = false, }; return __kvm_handle_hva_range(kvm, &range).ret; } static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn, unsigned long start, unsigned long end, gfn_handler_t handler) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range range = { .start = start, .end = end, .handler = handler, .on_lock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = false, }; return __kvm_handle_hva_range(kvm, &range).ret; } void kvm_mmu_invalidate_begin(struct kvm *kvm) { lockdep_assert_held_write(&kvm->mmu_lock); /* * The count increase must become visible at unlock time as no * spte can be established without taking the mmu_lock and * count is also read inside the mmu_lock critical section. */ kvm->mmu_invalidate_in_progress++; if (likely(kvm->mmu_invalidate_in_progress == 1)) { kvm->mmu_invalidate_range_start = INVALID_GPA; kvm->mmu_invalidate_range_end = INVALID_GPA; } } void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end) { lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress); if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) { kvm->mmu_invalidate_range_start = start; kvm->mmu_invalidate_range_end = end; } else { /* * Fully tracking multiple concurrent ranges has diminishing * returns. Keep things simple and just find the minimal range * which includes the current and new ranges. As there won't be * enough information to subtract a range after its invalidate * completes, any ranges invalidated concurrently will * accumulate and persist until all outstanding invalidates * complete. */ kvm->mmu_invalidate_range_start = min(kvm->mmu_invalidate_range_start, start); kvm->mmu_invalidate_range_end = max(kvm->mmu_invalidate_range_end, end); } } bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { kvm_mmu_invalidate_range_add(kvm, range->start, range->end); return kvm_unmap_gfn_range(kvm, range); } static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, const struct mmu_notifier_range *range) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range hva_range = { .start = range->start, .end = range->end, .handler = kvm_mmu_unmap_gfn_range, .on_lock = kvm_mmu_invalidate_begin, .flush_on_ret = true, .may_block = mmu_notifier_range_blockable(range), }; trace_kvm_unmap_hva_range(range->start, range->end); /* * Prevent memslot modification between range_start() and range_end() * so that conditionally locking provides the same result in both * functions. Without that guarantee, the mmu_invalidate_in_progress * adjustments will be imbalanced. * * Pairs with the decrement in range_end(). */ spin_lock(&kvm->mn_invalidate_lock); kvm->mn_active_invalidate_count++; spin_unlock(&kvm->mn_invalidate_lock); /* * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e. * before acquiring mmu_lock, to avoid holding mmu_lock while acquiring * each cache's lock. There are relatively few caches in existence at * any given time, and the caches themselves can check for hva overlap, * i.e. don't need to rely on memslot overlap checks for performance. * Because this runs without holding mmu_lock, the pfn caches must use * mn_active_invalidate_count (see above) instead of * mmu_invalidate_in_progress. */ gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end); /* * If one or more memslots were found and thus zapped, notify arch code * that guest memory has been reclaimed. This needs to be done *after* * dropping mmu_lock, as x86's reclaim path is slooooow. */ if (__kvm_handle_hva_range(kvm, &hva_range).found_memslot) kvm_arch_guest_memory_reclaimed(kvm); return 0; } void kvm_mmu_invalidate_end(struct kvm *kvm) { lockdep_assert_held_write(&kvm->mmu_lock); /* * This sequence increase will notify the kvm page fault that * the page that is going to be mapped in the spte could have * been freed. */ kvm->mmu_invalidate_seq++; smp_wmb(); /* * The above sequence increase must be visible before the * below count decrease, which is ensured by the smp_wmb above * in conjunction with the smp_rmb in mmu_invalidate_retry(). */ kvm->mmu_invalidate_in_progress--; KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm); /* * Assert that at least one range was added between start() and end(). * Not adding a range isn't fatal, but it is a KVM bug. */ WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA); } static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, const struct mmu_notifier_range *range) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range hva_range = { .start = range->start, .end = range->end, .handler = (void *)kvm_null_fn, .on_lock = kvm_mmu_invalidate_end, .flush_on_ret = false, .may_block = mmu_notifier_range_blockable(range), }; bool wake; __kvm_handle_hva_range(kvm, &hva_range); /* Pairs with the increment in range_start(). */ spin_lock(&kvm->mn_invalidate_lock); if (!WARN_ON_ONCE(!kvm->mn_active_invalidate_count)) --kvm->mn_active_invalidate_count; wake = !kvm->mn_active_invalidate_count; spin_unlock(&kvm->mn_invalidate_lock); /* * There can only be one waiter, since the wait happens under * slots_lock. */ if (wake) rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait); } static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) { trace_kvm_age_hva(start, end); return kvm_handle_hva_range(mn, start, end, kvm_age_gfn); } static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) { trace_kvm_age_hva(start, end); /* * Even though we do not flush TLB, this will still adversely * affect performance on pre-Haswell Intel EPT, where there is * no EPT Access Bit to clear so that we have to tear down EPT * tables instead. If we find this unacceptable, we can always * add a parameter to kvm_age_hva so that it effectively doesn't * do anything on clear_young. * * Also note that currently we never issue secondary TLB flushes * from clear_young, leaving this job up to the regular system * cadence. If we find this inaccurate, we might come up with a * more sophisticated heuristic later. */ return kvm_handle_hva_range_no_flush(mn, start, end, kvm_age_gfn); } static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address) { trace_kvm_test_age_hva(address); return kvm_handle_hva_range_no_flush(mn, address, address + 1, kvm_test_age_gfn); } static void kvm_mmu_notifier_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct kvm *kvm = mmu_notifier_to_kvm(mn); int idx; idx = srcu_read_lock(&kvm->srcu); kvm_flush_shadow_all(kvm); srcu_read_unlock(&kvm->srcu, idx); } static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start, .invalidate_range_end = kvm_mmu_notifier_invalidate_range_end, .clear_flush_young = kvm_mmu_notifier_clear_flush_young, .clear_young = kvm_mmu_notifier_clear_young, .test_young = kvm_mmu_notifier_test_young, .release = kvm_mmu_notifier_release, }; static int kvm_init_mmu_notifier(struct kvm *kvm) { kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops; return mmu_notifier_register(&kvm->mmu_notifier, current->mm); } #else /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */ static int kvm_init_mmu_notifier(struct kvm *kvm) { return 0; } #endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */ #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_pm_notifier_call(struct notifier_block *bl, unsigned long state, void *unused) { struct kvm *kvm = container_of(bl, struct kvm, pm_notifier); return kvm_arch_pm_notifier(kvm, state); } static void kvm_init_pm_notifier(struct kvm *kvm) { kvm->pm_notifier.notifier_call = kvm_pm_notifier_call; /* Suspend KVM before we suspend ftrace, RCU, etc. */ kvm->pm_notifier.priority = INT_MAX; register_pm_notifier(&kvm->pm_notifier); } static void kvm_destroy_pm_notifier(struct kvm *kvm) { unregister_pm_notifier(&kvm->pm_notifier); } #else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */ static void kvm_init_pm_notifier(struct kvm *kvm) { } static void kvm_destroy_pm_notifier(struct kvm *kvm) { } #endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) { if (!memslot->dirty_bitmap) return; vfree(memslot->dirty_bitmap); memslot->dirty_bitmap = NULL; } /* This does not remove the slot from struct kvm_memslots data structures */ static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { if (slot->flags & KVM_MEM_GUEST_MEMFD) kvm_gmem_unbind(slot); kvm_destroy_dirty_bitmap(slot); kvm_arch_free_memslot(kvm, slot); kfree(slot); } static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) { struct hlist_node *idnode; struct kvm_memory_slot *memslot; int bkt; /* * The same memslot objects live in both active and inactive sets, * arbitrarily free using index '1' so the second invocation of this * function isn't operating over a structure with dangling pointers * (even though this function isn't actually touching them). */ if (!slots->node_idx) return; hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1]) kvm_free_memslot(kvm, memslot); } static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) { switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) { case KVM_STATS_TYPE_INSTANT: return 0444; case KVM_STATS_TYPE_CUMULATIVE: case KVM_STATS_TYPE_PEAK: default: return 0644; } } static void kvm_destroy_vm_debugfs(struct kvm *kvm) { int i; int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; if (IS_ERR(kvm->debugfs_dentry)) return; debugfs_remove_recursive(kvm->debugfs_dentry); if (kvm->debugfs_stat_data) { for (i = 0; i < kvm_debugfs_num_entries; i++) kfree(kvm->debugfs_stat_data[i]); kfree(kvm->debugfs_stat_data); } } static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname) { static DEFINE_MUTEX(kvm_debugfs_lock); struct dentry *dent; char dir_name[ITOA_MAX_LEN * 2]; struct kvm_stat_data *stat_data; const struct _kvm_stats_desc *pdesc; int i, ret = -ENOMEM; int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; if (!debugfs_initialized()) return 0; snprintf(dir_name, sizeof(dir_name), "%d-%s", task_pid_nr(current), fdname); mutex_lock(&kvm_debugfs_lock); dent = debugfs_lookup(dir_name, kvm_debugfs_dir); if (dent) { pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name); dput(dent); mutex_unlock(&kvm_debugfs_lock); return 0; } dent = debugfs_create_dir(dir_name, kvm_debugfs_dir); mutex_unlock(&kvm_debugfs_lock); if (IS_ERR(dent)) return 0; kvm->debugfs_dentry = dent; kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries, sizeof(*kvm->debugfs_stat_data), GFP_KERNEL_ACCOUNT); if (!kvm->debugfs_stat_data) goto out_err; for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { pdesc = &kvm_vm_stats_desc[i]; stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); if (!stat_data) goto out_err; stat_data->kvm = kvm; stat_data->desc = pdesc; stat_data->kind = KVM_STAT_VM; kvm->debugfs_stat_data[i] = stat_data; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); } for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { pdesc = &kvm_vcpu_stats_desc[i]; stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); if (!stat_data) goto out_err; stat_data->kvm = kvm; stat_data->desc = pdesc; stat_data->kind = KVM_STAT_VCPU; kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); } kvm_arch_create_vm_debugfs(kvm); return 0; out_err: kvm_destroy_vm_debugfs(kvm); return ret; } /* * Called after the VM is otherwise initialized, but just before adding it to * the vm_list. */ int __weak kvm_arch_post_init_vm(struct kvm *kvm) { return 0; } /* * Called just after removing the VM from the vm_list, but before doing any * other destruction. */ void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm) { } /* * Called after per-vm debugfs created. When called kvm->debugfs_dentry should * be setup already, so we can create arch-specific debugfs entries under it. * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so * a per-arch destroy interface is not needed. */ void __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) { } static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) { struct kvm *kvm = kvm_arch_alloc_vm(); struct kvm_memslots *slots; int r, i, j; if (!kvm) return ERR_PTR(-ENOMEM); KVM_MMU_LOCK_INIT(kvm); mmgrab(current->mm); kvm->mm = current->mm; kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); mutex_init(&kvm->slots_lock); mutex_init(&kvm->slots_arch_lock); spin_lock_init(&kvm->mn_invalidate_lock); rcuwait_init(&kvm->mn_memslots_update_rcuwait); xa_init(&kvm->vcpu_array); #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES xa_init(&kvm->mem_attr_array); #endif INIT_LIST_HEAD(&kvm->gpc_list); spin_lock_init(&kvm->gpc_lock); INIT_LIST_HEAD(&kvm->devices); kvm->max_vcpus = KVM_MAX_VCPUS; BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); /* * Force subsequent debugfs file creations to fail if the VM directory * is not created (by kvm_create_vm_debugfs()). */ kvm->debugfs_dentry = ERR_PTR(-ENOENT); snprintf(kvm->stats_id, sizeof(kvm->stats_id), "kvm-%d", task_pid_nr(current)); r = -ENOMEM; if (init_srcu_struct(&kvm->srcu)) goto out_err_no_srcu; if (init_srcu_struct(&kvm->irq_srcu)) goto out_err_no_irq_srcu; r = kvm_init_irq_routing(kvm); if (r) goto out_err_no_irq_routing; refcount_set(&kvm->users_count, 1); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { for (j = 0; j < 2; j++) { slots = &kvm->__memslots[i][j]; atomic_long_set(&slots->last_used_slot, (unsigned long)NULL); slots->hva_tree = RB_ROOT_CACHED; slots->gfn_tree = RB_ROOT; hash_init(slots->id_hash); slots->node_idx = j; /* Generations must be different for each address space. */ slots->generation = i; } rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]); } r = -ENOMEM; for (i = 0; i < KVM_NR_BUSES; i++) { rcu_assign_pointer(kvm->buses[i], kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT)); if (!kvm->buses[i]) goto out_err_no_arch_destroy_vm; } r = kvm_arch_init_vm(kvm, type); if (r) goto out_err_no_arch_destroy_vm; r = hardware_enable_all(); if (r) goto out_err_no_disable; #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif r = kvm_init_mmu_notifier(kvm); if (r) goto out_err_no_mmu_notifier; r = kvm_coalesced_mmio_init(kvm); if (r < 0) goto out_no_coalesced_mmio; r = kvm_create_vm_debugfs(kvm, fdname); if (r) goto out_err_no_debugfs; r = kvm_arch_post_init_vm(kvm); if (r) goto out_err; mutex_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); mutex_unlock(&kvm_lock); preempt_notifier_inc(); kvm_init_pm_notifier(kvm); return kvm; out_err: kvm_destroy_vm_debugfs(kvm); out_err_no_debugfs: kvm_coalesced_mmio_free(kvm); out_no_coalesced_mmio: #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER if (kvm->mmu_notifier.ops) mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); #endif out_err_no_mmu_notifier: hardware_disable_all(); out_err_no_disable: kvm_arch_destroy_vm(kvm); out_err_no_arch_destroy_vm: WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm_get_bus(kvm, i)); kvm_free_irq_routing(kvm); out_err_no_irq_routing: cleanup_srcu_struct(&kvm->irq_srcu); out_err_no_irq_srcu: cleanup_srcu_struct(&kvm->srcu); out_err_no_srcu: kvm_arch_free_vm(kvm); mmdrop(current->mm); return ERR_PTR(r); } static void kvm_destroy_devices(struct kvm *kvm) { struct kvm_device *dev, *tmp; /* * We do not need to take the kvm->lock here, because nobody else * has a reference to the struct kvm at this point and therefore * cannot access the devices list anyhow. * * The device list is generally managed as an rculist, but list_del() * is used intentionally here. If a bug in KVM introduced a reader that * was not backed by a reference on the kvm struct, the hope is that * it'd consume the poisoned forward pointer instead of suffering a * use-after-free, even though this cannot be guaranteed. */ list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) { list_del(&dev->vm_node); dev->ops->destroy(dev); } } static void kvm_destroy_vm(struct kvm *kvm) { int i; struct mm_struct *mm = kvm->mm; kvm_destroy_pm_notifier(kvm); kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm); kvm_destroy_vm_debugfs(kvm); kvm_arch_sync_events(kvm); mutex_lock(&kvm_lock); list_del(&kvm->vm_list); mutex_unlock(&kvm_lock); kvm_arch_pre_destroy_vm(kvm); kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) { struct kvm_io_bus *bus = kvm_get_bus(kvm, i); if (bus) kvm_io_bus_destroy(bus); kvm->buses[i] = NULL; } kvm_coalesced_mmio_free(kvm); #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); /* * At this point, pending calls to invalidate_range_start() * have completed but no more MMU notifiers will run, so * mn_active_invalidate_count may remain unbalanced. * No threads can be waiting in kvm_swap_active_memslots() as the * last reference on KVM has been dropped, but freeing * memslots would deadlock without this manual intervention. * * If the count isn't unbalanced, i.e. KVM did NOT unregister its MMU * notifier between a start() and end(), then there shouldn't be any * in-progress invalidations. */ WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); if (kvm->mn_active_invalidate_count) kvm->mn_active_invalidate_count = 0; else WARN_ON(kvm->mmu_invalidate_in_progress); #else kvm_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { kvm_free_memslots(kvm, &kvm->__memslots[i][0]); kvm_free_memslots(kvm, &kvm->__memslots[i][1]); } cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES xa_destroy(&kvm->mem_attr_array); #endif kvm_arch_free_vm(kvm); preempt_notifier_dec(); hardware_disable_all(); mmdrop(mm); } void kvm_get_kvm(struct kvm *kvm) { refcount_inc(&kvm->users_count); } EXPORT_SYMBOL_GPL(kvm_get_kvm); /* * Make sure the vm is not during destruction, which is a safe version of * kvm_get_kvm(). Return true if kvm referenced successfully, false otherwise. */ bool kvm_get_kvm_safe(struct kvm *kvm) { return refcount_inc_not_zero(&kvm->users_count); } EXPORT_SYMBOL_GPL(kvm_get_kvm_safe); void kvm_put_kvm(struct kvm *kvm) { if (refcount_dec_and_test(&kvm->users_count)) kvm_destroy_vm(kvm); } EXPORT_SYMBOL_GPL(kvm_put_kvm); /* * Used to put a reference that was taken on behalf of an object associated * with a user-visible file descriptor, e.g. a vcpu or device, if installation * of the new file descriptor fails and the reference cannot be transferred to * its final owner. In such cases, the caller is still actively using @kvm and * will fail miserably if the refcount unexpectedly hits zero. */ void kvm_put_kvm_no_destroy(struct kvm *kvm) { WARN_ON(refcount_dec_and_test(&kvm->users_count)); } EXPORT_SYMBOL_GPL(kvm_put_kvm_no_destroy); static int kvm_vm_release(struct inode *inode, struct file *filp) { struct kvm *kvm = filp->private_data; kvm_irqfd_release(kvm); kvm_put_kvm(kvm); return 0; } /* * Allocation size is twice as large as the actual dirty bitmap size. * See kvm_vm_ioctl_get_dirty_log() why this is needed. */ static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) { unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(memslot); memslot->dirty_bitmap = __vcalloc(2, dirty_bytes, GFP_KERNEL_ACCOUNT); if (!memslot->dirty_bitmap) return -ENOMEM; return 0; } static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id) { struct kvm_memslots *active = __kvm_memslots(kvm, as_id); int node_idx_inactive = active->node_idx ^ 1; return &kvm->__memslots[as_id][node_idx_inactive]; } /* * Helper to get the address space ID when one of memslot pointers may be NULL. * This also serves as a sanity that at least one of the pointers is non-NULL, * and that their address space IDs don't diverge. */ static int kvm_memslots_get_as_id(struct kvm_memory_slot *a, struct kvm_memory_slot *b) { if (WARN_ON_ONCE(!a && !b)) return 0; if (!a) return b->as_id; if (!b) return a->as_id; WARN_ON_ONCE(a->as_id != b->as_id); return a->as_id; } static void kvm_insert_gfn_node(struct kvm_memslots *slots, struct kvm_memory_slot *slot) { struct rb_root *gfn_tree = &slots->gfn_tree; struct rb_node **node, *parent; int idx = slots->node_idx; parent = NULL; for (node = &gfn_tree->rb_node; *node; ) { struct kvm_memory_slot *tmp; tmp = container_of(*node, struct kvm_memory_slot, gfn_node[idx]); parent = *node; if (slot->base_gfn < tmp->base_gfn) node = &(*node)->rb_left; else if (slot->base_gfn > tmp->base_gfn) node = &(*node)->rb_right; else BUG(); } rb_link_node(&slot->gfn_node[idx], parent, node); rb_insert_color(&slot->gfn_node[idx], gfn_tree); } static void kvm_erase_gfn_node(struct kvm_memslots *slots, struct kvm_memory_slot *slot) { rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree); } static void kvm_replace_gfn_node(struct kvm_memslots *slots, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { int idx = slots->node_idx; WARN_ON_ONCE(old->base_gfn != new->base_gfn); rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx], &slots->gfn_tree); } /* * Replace @old with @new in the inactive memslots. * * With NULL @old this simply adds @new. * With NULL @new this simply removes @old. * * If @new is non-NULL its hva_node[slots_idx] range has to be set * appropriately. */ static void kvm_replace_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { int as_id = kvm_memslots_get_as_id(old, new); struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); int idx = slots->node_idx; if (old) { hash_del(&old->id_node[idx]); interval_tree_remove(&old->hva_node[idx], &slots->hva_tree); if ((long)old == atomic_long_read(&slots->last_used_slot)) atomic_long_set(&slots->last_used_slot, (long)new); if (!new) { kvm_erase_gfn_node(slots, old); return; } } /* * Initialize @new's hva range. Do this even when replacing an @old * slot, kvm_copy_memslot() deliberately does not touch node data. */ new->hva_node[idx].start = new->userspace_addr; new->hva_node[idx].last = new->userspace_addr + (new->npages << PAGE_SHIFT) - 1; /* * (Re)Add the new memslot. There is no O(1) interval_tree_replace(), * hva_node needs to be swapped with remove+insert even though hva can't * change when replacing an existing slot. */ hash_add(slots->id_hash, &new->id_node[idx], new->id); interval_tree_insert(&new->hva_node[idx], &slots->hva_tree); /* * If the memslot gfn is unchanged, rb_replace_node() can be used to * switch the node in the gfn tree instead of removing the old and * inserting the new as two separate operations. Replacement is a * single O(1) operation versus two O(log(n)) operations for * remove+insert. */ if (old && old->base_gfn == new->base_gfn) { kvm_replace_gfn_node(slots, old, new); } else { if (old) kvm_erase_gfn_node(slots, old); kvm_insert_gfn_node(slots, new); } } /* * Flags that do not access any of the extra space of struct * kvm_userspace_memory_region2. KVM_SET_USER_MEMORY_REGION_V1_FLAGS * only allows these. */ #define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \ (KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY) static int check_memory_region_flags(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; if (kvm_arch_has_private_mem(kvm)) valid_flags |= KVM_MEM_GUEST_MEMFD; /* Dirty logging private memory is not currently supported. */ if (mem->flags & KVM_MEM_GUEST_MEMFD) valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; #ifdef CONFIG_HAVE_KVM_READONLY_MEM /* * GUEST_MEMFD is incompatible with read-only memslots, as writes to * read-only memslots have emulated MMIO, not page fault, semantics, * and KVM doesn't allow emulated MMIO for private memory. */ if (!(mem->flags & KVM_MEM_GUEST_MEMFD)) valid_flags |= KVM_MEM_READONLY; #endif if (mem->flags & ~valid_flags) return -EINVAL; return 0; } static void kvm_swap_active_memslots(struct kvm *kvm, int as_id) { struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); /* Grab the generation from the activate memslots. */ u64 gen = __kvm_memslots(kvm, as_id)->generation; WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; /* * Do not store the new memslots while there are invalidations in * progress, otherwise the locking in invalidate_range_start and * invalidate_range_end will be unbalanced. */ spin_lock(&kvm->mn_invalidate_lock); prepare_to_rcuwait(&kvm->mn_memslots_update_rcuwait); while (kvm->mn_active_invalidate_count) { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&kvm->mn_invalidate_lock); schedule(); spin_lock(&kvm->mn_invalidate_lock); } finish_rcuwait(&kvm->mn_memslots_update_rcuwait); rcu_assign_pointer(kvm->memslots[as_id], slots); spin_unlock(&kvm->mn_invalidate_lock); /* * Acquired in kvm_set_memslot. Must be released before synchronize * SRCU below in order to avoid deadlock with another thread * acquiring the slots_arch_lock in an srcu critical section. */ mutex_unlock(&kvm->slots_arch_lock); synchronize_srcu_expedited(&kvm->srcu); /* * Increment the new memslot generation a second time, dropping the * update in-progress flag and incrementing the generation based on * the number of address spaces. This provides a unique and easily * identifiable generation number while the memslots are in flux. */ gen = slots->generation & ~KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; /* * Generations must be unique even across address spaces. We do not need * a global counter for that, instead the generation space is evenly split * across address spaces. For example, with two address spaces, address * space 0 will use generations 0, 2, 4, ... while address space 1 will * use generations 1, 3, 5, ... */ gen += kvm_arch_nr_memslot_as_ids(kvm); kvm_arch_memslots_updated(kvm, gen); slots->generation = gen; } static int kvm_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { int r; /* * If dirty logging is disabled, nullify the bitmap; the old bitmap * will be freed on "commit". If logging is enabled in both old and * new, reuse the existing bitmap. If logging is enabled only in the * new and KVM isn't using a ring buffer, allocate and initialize a * new bitmap. */ if (change != KVM_MR_DELETE) { if (!(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) new->dirty_bitmap = NULL; else if (old && old->dirty_bitmap) new->dirty_bitmap = old->dirty_bitmap; else if (kvm_use_dirty_bitmap(kvm)) { r = kvm_alloc_dirty_bitmap(new); if (r) return r; if (kvm_dirty_log_manual_protect_and_init_set(kvm)) bitmap_set(new->dirty_bitmap, 0, new->npages); } } r = kvm_arch_prepare_memory_region(kvm, old, new, change); /* Free the bitmap on failure if it was allocated above. */ if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap)) kvm_destroy_dirty_bitmap(new); return r; } static void kvm_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { int old_flags = old ? old->flags : 0; int new_flags = new ? new->flags : 0; /* * Update the total number of memslot pages before calling the arch * hook so that architectures can consume the result directly. */ if (change == KVM_MR_DELETE) kvm->nr_memslot_pages -= old->npages; else if (change == KVM_MR_CREATE) kvm->nr_memslot_pages += new->npages; if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) { int change = (new_flags & KVM_MEM_LOG_DIRTY_PAGES) ? 1 : -1; atomic_set(&kvm->nr_memslots_dirty_logging, atomic_read(&kvm->nr_memslots_dirty_logging) + change); } kvm_arch_commit_memory_region(kvm, old, new, change); switch (change) { case KVM_MR_CREATE: /* Nothing more to do. */ break; case KVM_MR_DELETE: /* Free the old memslot and all its metadata. */ kvm_free_memslot(kvm, old); break; case KVM_MR_MOVE: case KVM_MR_FLAGS_ONLY: /* * Free the dirty bitmap as needed; the below check encompasses * both the flags and whether a ring buffer is being used) */ if (old->dirty_bitmap && !new->dirty_bitmap) kvm_destroy_dirty_bitmap(old); /* * The final quirk. Free the detached, old slot, but only its * memory, not any metadata. Metadata, including arch specific * data, may be reused by @new. */ kfree(old); break; default: BUG(); } } /* * Activate @new, which must be installed in the inactive slots by the caller, * by swapping the active slots and then propagating @new to @old once @old is * unreachable and can be safely modified. * * With NULL @old this simply adds @new to @active (while swapping the sets). * With NULL @new this simply removes @old from @active and frees it * (while also swapping the sets). */ static void kvm_activate_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { int as_id = kvm_memslots_get_as_id(old, new); kvm_swap_active_memslots(kvm, as_id); /* Propagate the new memslot to the now inactive memslots. */ kvm_replace_memslot(kvm, old, new); } static void kvm_copy_memslot(struct kvm_memory_slot *dest, const struct kvm_memory_slot *src) { dest->base_gfn = src->base_gfn; dest->npages = src->npages; dest->dirty_bitmap = src->dirty_bitmap; dest->arch = src->arch; dest->userspace_addr = src->userspace_addr; dest->flags = src->flags; dest->id = src->id; dest->as_id = src->as_id; } static void kvm_invalidate_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *invalid_slot) { /* * Mark the current slot INVALID. As with all memslot modifications, * this must be done on an unreachable slot to avoid modifying the * current slot in the active tree. */ kvm_copy_memslot(invalid_slot, old); invalid_slot->flags |= KVM_MEMSLOT_INVALID; kvm_replace_memslot(kvm, old, invalid_slot); /* * Activate the slot that is now marked INVALID, but don't propagate * the slot to the now inactive slots. The slot is either going to be * deleted or recreated as a new slot. */ kvm_swap_active_memslots(kvm, old->as_id); /* * From this point no new shadow pages pointing to a deleted, or moved, * memslot will be created. Validation of sp->gfn happens in: * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) * - kvm_is_visible_gfn (mmu_check_root) */ kvm_arch_flush_shadow_memslot(kvm, old); kvm_arch_guest_memory_reclaimed(kvm); /* Was released by kvm_swap_active_memslots(), reacquire. */ mutex_lock(&kvm->slots_arch_lock); /* * Copy the arch-specific field of the newly-installed slot back to the * old slot as the arch data could have changed between releasing * slots_arch_lock in kvm_swap_active_memslots() and re-acquiring the lock * above. Writers are required to retrieve memslots *after* acquiring * slots_arch_lock, thus the active slot's data is guaranteed to be fresh. */ old->arch = invalid_slot->arch; } static void kvm_create_memslot(struct kvm *kvm, struct kvm_memory_slot *new) { /* Add the new memslot to the inactive set and activate. */ kvm_replace_memslot(kvm, NULL, new); kvm_activate_memslot(kvm, NULL, new); } static void kvm_delete_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *invalid_slot) { /* * Remove the old memslot (in the inactive memslots) by passing NULL as * the "new" slot, and for the invalid version in the active slots. */ kvm_replace_memslot(kvm, old, NULL); kvm_activate_memslot(kvm, invalid_slot, NULL); } static void kvm_move_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new, struct kvm_memory_slot *invalid_slot) { /* * Replace the old memslot in the inactive slots, and then swap slots * and replace the current INVALID with the new as well. */ kvm_replace_memslot(kvm, old, new); kvm_activate_memslot(kvm, invalid_slot, new); } static void kvm_update_flags_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { /* * Similar to the MOVE case, but the slot doesn't need to be zapped as * an intermediate step. Instead, the old memslot is simply replaced * with a new, updated copy in both memslot sets. */ kvm_replace_memslot(kvm, old, new); kvm_activate_memslot(kvm, old, new); } static int kvm_set_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { struct kvm_memory_slot *invalid_slot; int r; /* * Released in kvm_swap_active_memslots(). * * Must be held from before the current memslots are copied until after * the new memslots are installed with rcu_assign_pointer, then * released before the synchronize srcu in kvm_swap_active_memslots(). * * When modifying memslots outside of the slots_lock, must be held * before reading the pointer to the current memslots until after all * changes to those memslots are complete. * * These rules ensure that installing new memslots does not lose * changes made to the previous memslots. */ mutex_lock(&kvm->slots_arch_lock); /* * Invalidate the old slot if it's being deleted or moved. This is * done prior to actually deleting/moving the memslot to allow vCPUs to * continue running by ensuring there are no mappings or shadow pages * for the memslot when it is deleted/moved. Without pre-invalidation * (and without a lock), a window would exist between effecting the * delete/move and committing the changes in arch code where KVM or a * guest could access a non-existent memslot. * * Modifications are done on a temporary, unreachable slot. The old * slot needs to be preserved in case a later step fails and the * invalidation needs to be reverted. */ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { invalid_slot = kzalloc(sizeof(*invalid_slot), GFP_KERNEL_ACCOUNT); if (!invalid_slot) { mutex_unlock(&kvm->slots_arch_lock); return -ENOMEM; } kvm_invalidate_memslot(kvm, old, invalid_slot); } r = kvm_prepare_memory_region(kvm, old, new, change); if (r) { /* * For DELETE/MOVE, revert the above INVALID change. No * modifications required since the original slot was preserved * in the inactive slots. Changing the active memslots also * release slots_arch_lock. */ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { kvm_activate_memslot(kvm, invalid_slot, old); kfree(invalid_slot); } else { mutex_unlock(&kvm->slots_arch_lock); } return r; } /* * For DELETE and MOVE, the working slot is now active as the INVALID * version of the old slot. MOVE is particularly special as it reuses * the old slot and returns a copy of the old slot (in working_slot). * For CREATE, there is no old slot. For DELETE and FLAGS_ONLY, the * old slot is detached but otherwise preserved. */ if (change == KVM_MR_CREATE) kvm_create_memslot(kvm, new); else if (change == KVM_MR_DELETE) kvm_delete_memslot(kvm, old, invalid_slot); else if (change == KVM_MR_MOVE) kvm_move_memslot(kvm, old, new, invalid_slot); else if (change == KVM_MR_FLAGS_ONLY) kvm_update_flags_memslot(kvm, old, new); else BUG(); /* Free the temporary INVALID slot used for DELETE and MOVE. */ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) kfree(invalid_slot); /* * No need to refresh new->arch, changes after dropping slots_arch_lock * will directly hit the final, active memslot. Architectures are * responsible for knowing that new->arch may be stale. */ kvm_commit_memory_region(kvm, old, new, change); return 0; } static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id, gfn_t start, gfn_t end) { struct kvm_memslot_iter iter; kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) { if (iter.slot->id != id) return true; } return false; } /* * Allocate some memory and give it an address in the guest physical address * space. * * Discontiguous memory is allowed, mostly for framebuffers. * * Must be called holding kvm->slots_lock for write. */ int __kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem) { struct kvm_memory_slot *old, *new; struct kvm_memslots *slots; enum kvm_mr_change change; unsigned long npages; gfn_t base_gfn; int as_id, id; int r; r = check_memory_region_flags(kvm, mem); if (r) return r; as_id = mem->slot >> 16; id = (u16)mem->slot; /* General sanity checks */ if ((mem->memory_size & (PAGE_SIZE - 1)) || (mem->memory_size != (unsigned long)mem->memory_size)) return -EINVAL; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) return -EINVAL; /* We can read the guest memory with __xxx_user() later on. */ if ((mem->userspace_addr & (PAGE_SIZE - 1)) || (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL; if (mem->flags & KVM_MEM_GUEST_MEMFD && (mem->guest_memfd_offset & (PAGE_SIZE - 1) || mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset)) return -EINVAL; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM) return -EINVAL; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) return -EINVAL; if ((mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES) return -EINVAL; slots = __kvm_memslots(kvm, as_id); /* * Note, the old memslot (and the pointer itself!) may be invalidated * and/or destroyed by kvm_set_memslot(). */ old = id_to_memslot(slots, id); if (!mem->memory_size) { if (!old || !old->npages) return -EINVAL; if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages)) return -EIO; return kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE); } base_gfn = (mem->guest_phys_addr >> PAGE_SHIFT); npages = (mem->memory_size >> PAGE_SHIFT); if (!old || !old->npages) { change = KVM_MR_CREATE; /* * To simplify KVM internals, the total number of pages across * all memslots must fit in an unsigned long. */ if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) return -EINVAL; } else { /* Modify an existing slot. */ /* Private memslots are immutable, they can only be deleted. */ if (mem->flags & KVM_MEM_GUEST_MEMFD) return -EINVAL; if ((mem->userspace_addr != old->userspace_addr) || (npages != old->npages) || ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) return -EINVAL; if (base_gfn != old->base_gfn) change = KVM_MR_MOVE; else if (mem->flags != old->flags) change = KVM_MR_FLAGS_ONLY; else /* Nothing to change. */ return 0; } if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) && kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages)) return -EEXIST; /* Allocate a slot that will persist in the memslot. */ new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); if (!new) return -ENOMEM; new->as_id = as_id; new->id = id; new->base_gfn = base_gfn; new->npages = npages; new->flags = mem->flags; new->userspace_addr = mem->userspace_addr; if (mem->flags & KVM_MEM_GUEST_MEMFD) { r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset); if (r) goto out; } r = kvm_set_memslot(kvm, old, new, change); if (r) goto out_unbind; return 0; out_unbind: if (mem->flags & KVM_MEM_GUEST_MEMFD) kvm_gmem_unbind(new); out: kfree(new); return r; } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); int kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem) { int r; mutex_lock(&kvm->slots_lock); r = __kvm_set_memory_region(kvm, mem); mutex_unlock(&kvm->slots_lock); return r; } EXPORT_SYMBOL_GPL(kvm_set_memory_region); static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region2 *mem) { if ((u16)mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; return kvm_set_memory_region(kvm, mem); } #ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT /** * kvm_get_dirty_log - get a snapshot of dirty pages * @kvm: pointer to kvm instance * @log: slot id and address to which we copy the log * @is_dirty: set to '1' if any dirty pages were found * @memslot: set to the associated memslot, always valid on success */ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty, struct kvm_memory_slot **memslot) { struct kvm_memslots *slots; int i, as_id, id; unsigned long n; unsigned long any = 0; /* Dirty ring tracking may be exclusive to dirty log tracking */ if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; *memslot = NULL; *is_dirty = 0; as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; slots = __kvm_memslots(kvm, as_id); *memslot = id_to_memslot(slots, id); if (!(*memslot) || !(*memslot)->dirty_bitmap) return -ENOENT; kvm_arch_sync_dirty_log(kvm, *memslot); n = kvm_dirty_bitmap_bytes(*memslot); for (i = 0; !any && i < n/sizeof(long); ++i) any = (*memslot)->dirty_bitmap[i]; if (copy_to_user(log->dirty_bitmap, (*memslot)->dirty_bitmap, n)) return -EFAULT; if (any) *is_dirty = 1; return 0; } EXPORT_SYMBOL_GPL(kvm_get_dirty_log); #else /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ /** * kvm_get_dirty_log_protect - get a snapshot of dirty pages * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address to which we copy the log * * We need to keep it in mind that VCPU threads can write to the bitmap * concurrently. So, to avoid losing track of dirty pages we keep the * following order: * * 1. Take a snapshot of the bit and clear it if needed. * 2. Write protect the corresponding page. * 3. Copy the snapshot to the userspace. * 4. Upon return caller flushes TLB's if needed. * * Between 2 and 4, the guest may write to the page using the remaining TLB * entry. This is not a problem because the page is reported dirty using * the snapshot taken before and step 4 ensures that writes done after * exiting to userspace will be logged for the next call. * */ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int i, as_id, id; unsigned long n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; bool flush; /* Dirty ring tracking may be exclusive to dirty log tracking */ if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); if (!memslot || !memslot->dirty_bitmap) return -ENOENT; dirty_bitmap = memslot->dirty_bitmap; kvm_arch_sync_dirty_log(kvm, memslot); n = kvm_dirty_bitmap_bytes(memslot); flush = false; if (kvm->manual_dirty_log_protect) { /* * Unlike kvm_get_dirty_log, we always return false in *flush, * because no flush is needed until KVM_CLEAR_DIRTY_LOG. There * is some code duplication between this function and * kvm_get_dirty_log, but hopefully all architecture * transition to kvm_get_dirty_log_protect and kvm_get_dirty_log * can be eliminated. */ dirty_bitmap_buffer = dirty_bitmap; } else { dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); memset(dirty_bitmap_buffer, 0, n); KVM_MMU_LOCK(kvm); for (i = 0; i < n / sizeof(long); i++) { unsigned long mask; gfn_t offset; if (!dirty_bitmap[i]) continue; flush = true; mask = xchg(&dirty_bitmap[i], 0); dirty_bitmap_buffer[i] = mask; offset = i * BITS_PER_LONG; kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); } KVM_MMU_UNLOCK(kvm); } if (flush) kvm_flush_remote_tlbs_memslot(kvm, memslot); if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) return -EFAULT; return 0; } /** * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot * @kvm: kvm instance * @log: slot id and address to which we copy the log * * Steps 1-4 below provide general overview of dirty page logging. See * kvm_get_dirty_log_protect() function description for additional details. * * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we * always flush the TLB (step 4) even if previous step failed and the dirty * bitmap may be corrupt. Regardless of previous outcome the KVM logging API * does not preclude user space subsequent dirty log read. Flushing TLB ensures * writes will be marked dirty for next log read. * * 1. Take a snapshot of the bit and clear it if needed. * 2. Write protect the corresponding page. * 3. Copy the snapshot to the userspace. * 4. Flush TLB's if needed. */ static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { int r; mutex_lock(&kvm->slots_lock); r = kvm_get_dirty_log_protect(kvm, log); mutex_unlock(&kvm->slots_lock); return r; } /** * kvm_clear_dirty_log_protect - clear dirty bits in the bitmap * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address from which to fetch the bitmap of dirty pages */ static int kvm_clear_dirty_log_protect(struct kvm *kvm, struct kvm_clear_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int as_id, id; gfn_t offset; unsigned long i, n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; bool flush; /* Dirty ring tracking may be exclusive to dirty log tracking */ if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; if (log->first_page & 63) return -EINVAL; slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); if (!memslot || !memslot->dirty_bitmap) return -ENOENT; dirty_bitmap = memslot->dirty_bitmap; n = ALIGN(log->num_pages, BITS_PER_LONG) / 8; if (log->first_page > memslot->npages || log->num_pages > memslot->npages - log->first_page || (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63))) return -EINVAL; kvm_arch_sync_dirty_log(kvm, memslot); flush = false; dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n)) return -EFAULT; KVM_MMU_LOCK(kvm); for (offset = log->first_page, i = offset / BITS_PER_LONG, n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--; i++, offset += BITS_PER_LONG) { unsigned long mask = *dirty_bitmap_buffer++; atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i]; if (!mask) continue; mask &= atomic_long_fetch_andnot(mask, p); /* * mask contains the bits that really have been cleared. This * never includes any bits beyond the length of the memslot (if * the length is not aligned to 64 pages), therefore it is not * a problem if userspace sets them in log->dirty_bitmap. */ if (mask) { flush = true; kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); } } KVM_MMU_UNLOCK(kvm); if (flush) kvm_flush_remote_tlbs_memslot(kvm, memslot); return 0; } static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) { int r; mutex_lock(&kvm->slots_lock); r = kvm_clear_dirty_log_protect(kvm, log); mutex_unlock(&kvm->slots_lock); return r; } #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES /* * Returns true if _all_ gfns in the range [@start, @end) have attributes * matching @attrs. */ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long attrs) { XA_STATE(xas, &kvm->mem_attr_array, start); unsigned long index; bool has_attrs; void *entry; rcu_read_lock(); if (!attrs) { has_attrs = !xas_find(&xas, end - 1); goto out; } has_attrs = true; for (index = start; index < end; index++) { do { entry = xas_next(&xas); } while (xas_retry(&xas, entry)); if (xas.xa_index != index || xa_to_value(entry) != attrs) { has_attrs = false; break; } } out: rcu_read_unlock(); return has_attrs; } static u64 kvm_supported_mem_attributes(struct kvm *kvm) { if (!kvm || kvm_arch_has_private_mem(kvm)) return KVM_MEMORY_ATTRIBUTE_PRIVATE; return 0; } static __always_inline void kvm_handle_gfn_range(struct kvm *kvm, struct kvm_mmu_notifier_range *range) { struct kvm_gfn_range gfn_range; struct kvm_memory_slot *slot; struct kvm_memslots *slots; struct kvm_memslot_iter iter; bool found_memslot = false; bool ret = false; int i; gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) { slot = iter.slot; gfn_range.slot = slot; gfn_range.start = max(range->start, slot->base_gfn); gfn_range.end = min(range->end, slot->base_gfn + slot->npages); if (gfn_range.start >= gfn_range.end) continue; if (!found_memslot) { found_memslot = true; KVM_MMU_LOCK(kvm); if (!IS_KVM_NULL_FN(range->on_lock)) range->on_lock(kvm); } ret |= range->handler(kvm, &gfn_range); } } if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); if (found_memslot) KVM_MMU_UNLOCK(kvm); } static bool kvm_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range) { /* * Unconditionally add the range to the invalidation set, regardless of * whether or not the arch callback actually needs to zap SPTEs. E.g. * if KVM supports RWX attributes in the future and the attributes are * going from R=>RW, zapping isn't strictly necessary. Unconditionally * adding the range allows KVM to require that MMU invalidations add at * least one range between begin() and end(), e.g. allows KVM to detect * bugs where the add() is missed. Relaxing the rule *might* be safe, * but it's not obvious that allowing new mappings while the attributes * are in flux is desirable or worth the complexity. */ kvm_mmu_invalidate_range_add(kvm, range->start, range->end); return kvm_arch_pre_set_memory_attributes(kvm, range); } /* Set @attributes for the gfn range [@start, @end). */ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long attributes) { struct kvm_mmu_notifier_range pre_set_range = { .start = start, .end = end, .handler = kvm_pre_set_memory_attributes, .on_lock = kvm_mmu_invalidate_begin, .flush_on_ret = true, .may_block = true, }; struct kvm_mmu_notifier_range post_set_range = { .start = start, .end = end, .arg.attributes = attributes, .handler = kvm_arch_post_set_memory_attributes, .on_lock = kvm_mmu_invalidate_end, .may_block = true, }; unsigned long i; void *entry; int r = 0; entry = attributes ? xa_mk_value(attributes) : NULL; mutex_lock(&kvm->slots_lock); /* Nothing to do if the entire range as the desired attributes. */ if (kvm_range_has_memory_attributes(kvm, start, end, attributes)) goto out_unlock; /* * Reserve memory ahead of time to avoid having to deal with failures * partway through setting the new attributes. */ for (i = start; i < end; i++) { r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT); if (r) goto out_unlock; } kvm_handle_gfn_range(kvm, &pre_set_range); for (i = start; i < end; i++) { r = xa_err(xa_store(&kvm->mem_attr_array, i, entry, GFP_KERNEL_ACCOUNT)); KVM_BUG_ON(r, kvm); } kvm_handle_gfn_range(kvm, &post_set_range); out_unlock: mutex_unlock(&kvm->slots_lock); return r; } static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm, struct kvm_memory_attributes *attrs) { gfn_t start, end; /* flags is currently not used. */ if (attrs->flags) return -EINVAL; if (attrs->attributes & ~kvm_supported_mem_attributes(kvm)) return -EINVAL; if (attrs->size == 0 || attrs->address + attrs->size < attrs->address) return -EINVAL; if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size)) return -EINVAL; start = attrs->address >> PAGE_SHIFT; end = (attrs->address + attrs->size) >> PAGE_SHIFT; /* * xarray tracks data using "unsigned long", and as a result so does * KVM. For simplicity, supports generic attributes only on 64-bit * architectures. */ BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long)); return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes); } #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { return __gfn_to_memslot(kvm_memslots(kvm), gfn); } EXPORT_SYMBOL_GPL(gfn_to_memslot); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu); u64 gen = slots->generation; struct kvm_memory_slot *slot; /* * This also protects against using a memslot from a different address space, * since different address spaces have different generation numbers. */ if (unlikely(gen != vcpu->last_used_slot_gen)) { vcpu->last_used_slot = NULL; vcpu->last_used_slot_gen = gen; } slot = try_get_memslot(vcpu->last_used_slot, gfn); if (slot) return slot; /* * Fall back to searching all memslots. We purposely use * search_memslots() instead of __gfn_to_memslot() to avoid * thrashing the VM-wide last_used_slot in kvm_memslots. */ slot = search_memslots(slots, gfn, false); if (slot) { vcpu->last_used_slot = slot; return slot; } return NULL; } bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn); return kvm_is_visible_memslot(memslot); } EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memory_slot *memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return kvm_is_visible_memslot(memslot); } EXPORT_SYMBOL_GPL(kvm_vcpu_is_visible_gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn) { struct vm_area_struct *vma; unsigned long addr, size; size = PAGE_SIZE; addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL); if (kvm_is_error_hva(addr)) return PAGE_SIZE; mmap_read_lock(current->mm); vma = find_vma(current->mm, addr); if (!vma) goto out; size = vma_kernel_pagesize(vma); out: mmap_read_unlock(current->mm); return size; } static bool memslot_is_readonly(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_READONLY; } static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages, bool write) { if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return KVM_HVA_ERR_BAD; if (memslot_is_readonly(slot) && write) return KVM_HVA_ERR_RO_BAD; if (nr_pages) *nr_pages = slot->npages - (gfn - slot->base_gfn); return __gfn_to_hva_memslot(slot, gfn); } static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages) { return __gfn_to_hva_many(slot, gfn, nr_pages, true); } unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { return gfn_to_hva_many(slot, gfn, NULL); } EXPORT_SYMBOL_GPL(gfn_to_hva_memslot); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL); } EXPORT_SYMBOL_GPL(gfn_to_hva); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_hva_many(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, NULL); } EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_hva); /* * Return the hva of a @gfn and the R/W attribute if possible. * * @slot: the kvm_memory_slot which contains @gfn * @gfn: the gfn to be translated * @writable: used to return the read/write attribute of the @slot if the hva * is valid and @writable is not NULL */ unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn, bool *writable) { unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false); if (!kvm_is_error_hva(hva) && writable) *writable = !memslot_is_readonly(slot); return hva; } unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable) { struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); return gfn_to_hva_memslot_prot(slot, gfn, writable); } unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return gfn_to_hva_memslot_prot(slot, gfn, writable); } static inline int check_user_page_hwpoison(unsigned long addr) { int rc, flags = FOLL_HWPOISON | FOLL_WRITE; rc = get_user_pages(addr, 1, flags, NULL); return rc == -EHWPOISON; } /* * The fast path to get the writable pfn which will be stored in @pfn, * true indicates success, otherwise false is returned. It's also the * only part that runs if we can in atomic context. */ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault, bool *writable, kvm_pfn_t *pfn) { struct page *page[1]; /* * Fast pin a writable pfn only if it is a write fault request * or the caller allows to map a writable pfn for a read fault * request. */ if (!(write_fault || writable)) return false; if (get_user_page_fast_only(addr, FOLL_WRITE, page)) { *pfn = page_to_pfn(page[0]); if (writable) *writable = true; return true; } return false; } /* * The slow path to get the pfn of the specified host virtual address, * 1 indicates success, -errno is returned if error is detected. */ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, bool interruptible, bool *writable, kvm_pfn_t *pfn) { /* * When a VCPU accesses a page that is not mapped into the secondary * MMU, we lookup the page using GUP to map it, so the guest VCPU can * make progress. We always want to honor NUMA hinting faults in that * case, because GUP usage corresponds to memory accesses from the VCPU. * Otherwise, we'd not trigger NUMA hinting faults once a page is * mapped into the secondary MMU and gets accessed by a VCPU. * * Note that get_user_page_fast_only() and FOLL_WRITE for now * implicitly honor NUMA hinting faults and don't need this flag. */ unsigned int flags = FOLL_HWPOISON | FOLL_HONOR_NUMA_FAULT; struct page *page; int npages; might_sleep(); if (writable) *writable = write_fault; if (write_fault) flags |= FOLL_WRITE; if (async) flags |= FOLL_NOWAIT; if (interruptible) flags |= FOLL_INTERRUPTIBLE; npages = get_user_pages_unlocked(addr, 1, &page, flags); if (npages != 1) return npages; /* map read fault as writable if possible */ if (unlikely(!write_fault) && writable) { struct page *wpage; if (get_user_page_fast_only(addr, FOLL_WRITE, &wpage)) { *writable = true; put_page(page); page = wpage; } } *pfn = page_to_pfn(page); return npages; } static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) { if (unlikely(!(vma->vm_flags & VM_READ))) return false; if (write_fault && (unlikely(!(vma->vm_flags & VM_WRITE)))) return false; return true; } static int kvm_try_get_pfn(kvm_pfn_t pfn) { struct page *page = kvm_pfn_to_refcounted_page(pfn); if (!page) return 1; return get_page_unless_zero(page); } static int hva_to_pfn_remapped(struct vm_area_struct *vma, unsigned long addr, bool write_fault, bool *writable, kvm_pfn_t *p_pfn) { kvm_pfn_t pfn; pte_t *ptep; pte_t pte; spinlock_t *ptl; int r; r = follow_pte(vma, addr, &ptep, &ptl); if (r) { /* * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does * not call the fault handler, so do it here. */ bool unlocked = false; r = fixup_user_fault(current->mm, addr, (write_fault ? FAULT_FLAG_WRITE : 0), &unlocked); if (unlocked) return -EAGAIN; if (r) return r; r = follow_pte(vma, addr, &ptep, &ptl); if (r) return r; } pte = ptep_get(ptep); if (write_fault && !pte_write(pte)) { pfn = KVM_PFN_ERR_RO_FAULT; goto out; } if (writable) *writable = pte_write(pte); pfn = pte_pfn(pte); /* * Get a reference here because callers of *hva_to_pfn* and * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the * returned pfn. This is only needed if the VMA has VM_MIXEDMAP * set, but the kvm_try_get_pfn/kvm_release_pfn_clean pair will * simply do nothing for reserved pfns. * * Whoever called remap_pfn_range is also going to call e.g. * unmap_mapping_range before the underlying pages are freed, * causing a call to our MMU notifier. * * Certain IO or PFNMAP mappings can be backed with valid * struct pages, but be allocated without refcounting e.g., * tail pages of non-compound higher order allocations, which * would then underflow the refcount when the caller does the * required put_page. Don't allow those pages here. */ if (!kvm_try_get_pfn(pfn)) r = -EFAULT; out: pte_unmap_unlock(ptep, ptl); *p_pfn = pfn; return r; } /* * Pin guest page in memory and return its pfn. * @addr: host virtual address which maps memory to the guest * @atomic: whether this function is forbidden from sleeping * @interruptible: whether the process can be interrupted by non-fatal signals * @async: whether this function need to wait IO complete if the * host page is not in the memory * @write_fault: whether we should get a writable host page * @writable: whether it allows to map a writable host page for !@write_fault * * The function will map a writable host page for these two cases: * 1): @write_fault = true * 2): @write_fault = false && @writable, @writable will tell the caller * whether the mapping is writable. */ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible, bool *async, bool write_fault, bool *writable) { struct vm_area_struct *vma; kvm_pfn_t pfn; int npages, r; /* we can do it either atomically or asynchronously, not both */ BUG_ON(atomic && async); if (hva_to_pfn_fast(addr, write_fault, writable, &pfn)) return pfn; if (atomic) return KVM_PFN_ERR_FAULT; npages = hva_to_pfn_slow(addr, async, write_fault, interruptible, writable, &pfn); if (npages == 1) return pfn; if (npages == -EINTR) return KVM_PFN_ERR_SIGPENDING; mmap_read_lock(current->mm); if (npages == -EHWPOISON || (!async && check_user_page_hwpoison(addr))) { pfn = KVM_PFN_ERR_HWPOISON; goto exit; } retry: vma = vma_lookup(current->mm, addr); if (vma == NULL) pfn = KVM_PFN_ERR_FAULT; else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) { r = hva_to_pfn_remapped(vma, addr, write_fault, writable, &pfn); if (r == -EAGAIN) goto retry; if (r < 0) pfn = KVM_PFN_ERR_FAULT; } else { if (async && vma_is_valid(vma, write_fault)) *async = true; pfn = KVM_PFN_ERR_FAULT; } exit: mmap_read_unlock(current->mm); return pfn; } kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool interruptible, bool *async, bool write_fault, bool *writable, hva_t *hva) { unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); if (hva) *hva = addr; if (kvm_is_error_hva(addr)) { if (writable) *writable = false; return addr == KVM_HVA_ERR_RO_BAD ? KVM_PFN_ERR_RO_FAULT : KVM_PFN_NOSLOT; } /* Do not map writable pfn in the readonly memslot. */ if (writable && memslot_is_readonly(slot)) { *writable = false; writable = NULL; } return hva_to_pfn(addr, atomic, interruptible, async, write_fault, writable); } EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot); kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable) { return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, false, NULL, write_fault, writable, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, false, false, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, true, false, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); } EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic); kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) { return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn); } EXPORT_SYMBOL_GPL(gfn_to_pfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); } EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn); int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, struct page **pages, int nr_pages) { unsigned long addr; gfn_t entry = 0; addr = gfn_to_hva_many(slot, gfn, &entry); if (kvm_is_error_hva(addr)) return -1; if (entry < nr_pages) return 0; return get_user_pages_fast_only(addr, nr_pages, FOLL_WRITE, pages); } EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic); /* * Do not use this helper unless you are absolutely certain the gfn _must_ be * backed by 'struct page'. A valid example is if the backing memslot is * controlled by KVM. Note, if the returned page is valid, it's refcount has * been elevated by gfn_to_pfn(). */ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { struct page *page; kvm_pfn_t pfn; pfn = gfn_to_pfn(kvm, gfn); if (is_error_noslot_pfn(pfn)) return KVM_ERR_PTR_BAD_PAGE; page = kvm_pfn_to_refcounted_page(pfn); if (!page) return KVM_ERR_PTR_BAD_PAGE; return page; } EXPORT_SYMBOL_GPL(gfn_to_page); void kvm_release_pfn(kvm_pfn_t pfn, bool dirty) { if (dirty) kvm_release_pfn_dirty(pfn); else kvm_release_pfn_clean(pfn); } int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) { kvm_pfn_t pfn; void *hva = NULL; struct page *page = KVM_UNMAPPED_PAGE; if (!map) return -EINVAL; pfn = gfn_to_pfn(vcpu->kvm, gfn); if (is_error_noslot_pfn(pfn)) return -EINVAL; if (pfn_valid(pfn)) { page = pfn_to_page(pfn); hva = kmap(page); #ifdef CONFIG_HAS_IOMEM } else { hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); #endif } if (!hva) return -EFAULT; map->page = page; map->hva = hva; map->pfn = pfn; map->gfn = gfn; return 0; } EXPORT_SYMBOL_GPL(kvm_vcpu_map); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty) { if (!map) return; if (!map->hva) return; if (map->page != KVM_UNMAPPED_PAGE) kunmap(map->page); #ifdef CONFIG_HAS_IOMEM else memunmap(map->hva); #endif if (dirty) kvm_vcpu_mark_page_dirty(vcpu, map->gfn); kvm_release_pfn(map->pfn, dirty); map->hva = NULL; map->page = NULL; } EXPORT_SYMBOL_GPL(kvm_vcpu_unmap); static bool kvm_is_ad_tracked_page(struct page *page) { /* * Per page-flags.h, pages tagged PG_reserved "should in general not be * touched (e.g. set dirty) except by its owner". */ return !PageReserved(page); } static void kvm_set_page_dirty(struct page *page) { if (kvm_is_ad_tracked_page(page)) SetPageDirty(page); } static void kvm_set_page_accessed(struct page *page) { if (kvm_is_ad_tracked_page(page)) mark_page_accessed(page); } void kvm_release_page_clean(struct page *page) { WARN_ON(is_error_page(page)); kvm_set_page_accessed(page); put_page(page); } EXPORT_SYMBOL_GPL(kvm_release_page_clean); void kvm_release_pfn_clean(kvm_pfn_t pfn) { struct page *page; if (is_error_noslot_pfn(pfn)) return; page = kvm_pfn_to_refcounted_page(pfn); if (!page) return; kvm_release_page_clean(page); } EXPORT_SYMBOL_GPL(kvm_release_pfn_clean); void kvm_release_page_dirty(struct page *page) { WARN_ON(is_error_page(page)); kvm_set_page_dirty(page); kvm_release_page_clean(page); } EXPORT_SYMBOL_GPL(kvm_release_page_dirty); void kvm_release_pfn_dirty(kvm_pfn_t pfn) { struct page *page; if (is_error_noslot_pfn(pfn)) return; page = kvm_pfn_to_refcounted_page(pfn); if (!page) return; kvm_release_page_dirty(page); } EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty); /* * Note, checking for an error/noslot pfn is the caller's responsibility when * directly marking a page dirty/accessed. Unlike the "release" helpers, the * "set" helpers are not to be used when the pfn might point at garbage. */ void kvm_set_pfn_dirty(kvm_pfn_t pfn) { if (WARN_ON(is_error_noslot_pfn(pfn))) return; if (pfn_valid(pfn)) kvm_set_page_dirty(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); void kvm_set_pfn_accessed(kvm_pfn_t pfn) { if (WARN_ON(is_error_noslot_pfn(pfn))) return; if (pfn_valid(pfn)) kvm_set_page_accessed(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); static int next_segment(unsigned long len, int offset) { if (len > PAGE_SIZE - offset) return PAGE_SIZE - offset; else return len; } /* Copy @len bytes from guest memory at '(@gfn * PAGE_SIZE) + @offset' to @data */ static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn, void *data, int offset, int len) { int r; unsigned long addr; addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_from_user(data, (void __user *)addr + offset, len); if (r) return -EFAULT; return 0; } int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len) { struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); return __kvm_read_guest_page(slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_read_guest_page); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, int len) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return __kvm_read_guest_page(slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_page); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_read_guest_page(kvm, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_read_guest); int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_vcpu_read_guest_page(vcpu, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest); static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn, void *data, int offset, unsigned long len) { int r; unsigned long addr; addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len); pagefault_enable(); if (r) return -EFAULT; return 0; } int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); int offset = offset_in_page(gpa); return __kvm_read_guest_atomic(slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic); /* Copy @len bytes from @data into guest memory at '(@gfn * PAGE_SIZE) + @offset' */ static int __kvm_write_guest_page(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn, const void *data, int offset, int len) { int r; unsigned long addr; addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_to_user((void __user *)addr + offset, data, len); if (r) return -EFAULT; mark_page_dirty_in_slot(kvm, memslot, gfn); return 0; } int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len) { struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); return __kvm_write_guest_page(kvm, slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_write_guest_page); int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data, int offset, int len) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return __kvm_write_guest_page(vcpu->kvm, slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_write_guest_page(kvm, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_write_guest); int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_vcpu_write_guest_page(vcpu, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest); static int __kvm_gfn_to_hva_cache_init(struct kvm_memslots *slots, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len) { int offset = offset_in_page(gpa); gfn_t start_gfn = gpa >> PAGE_SHIFT; gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT; gfn_t nr_pages_needed = end_gfn - start_gfn + 1; gfn_t nr_pages_avail; /* Update ghc->generation before performing any error checks. */ ghc->generation = slots->generation; if (start_gfn > end_gfn) { ghc->hva = KVM_HVA_ERR_BAD; return -EINVAL; } /* * If the requested region crosses two memslots, we still * verify that the entire region is valid here. */ for ( ; start_gfn <= end_gfn; start_gfn += nr_pages_avail) { ghc->memslot = __gfn_to_memslot(slots, start_gfn); ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail); if (kvm_is_error_hva(ghc->hva)) return -EFAULT; } /* Use the slow path for cross page reads and writes. */ if (nr_pages_needed == 1) ghc->hva += offset; else ghc->memslot = NULL; ghc->gpa = gpa; ghc->len = len; return 0; } int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); return __kvm_gfn_to_hva_cache_init(slots, ghc, gpa, len); } EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init); int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); int r; gpa_t gpa = ghc->gpa + offset; if (WARN_ON_ONCE(len + offset > ghc->len)) return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) return -EFAULT; } if (kvm_is_error_hva(ghc->hva)) return -EFAULT; if (unlikely(!ghc->memslot)) return kvm_write_guest(kvm, gpa, data, len); r = __copy_to_user((void __user *)ghc->hva + offset, data, len); if (r) return -EFAULT; mark_page_dirty_in_slot(kvm, ghc->memslot, gpa >> PAGE_SHIFT); return 0; } EXPORT_SYMBOL_GPL(kvm_write_guest_offset_cached); int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len) { return kvm_write_guest_offset_cached(kvm, ghc, data, 0, len); } EXPORT_SYMBOL_GPL(kvm_write_guest_cached); int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); int r; gpa_t gpa = ghc->gpa + offset; if (WARN_ON_ONCE(len + offset > ghc->len)) return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) return -EFAULT; } if (kvm_is_error_hva(ghc->hva)) return -EFAULT; if (unlikely(!ghc->memslot)) return kvm_read_guest(kvm, gpa, data, len); r = __copy_from_user(data, (void __user *)ghc->hva + offset, len); if (r) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(kvm_read_guest_offset_cached); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len) { return kvm_read_guest_offset_cached(kvm, ghc, data, 0, len); } EXPORT_SYMBOL_GPL(kvm_read_guest_cached); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) { const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, len); if (ret < 0) return ret; offset = 0; len -= seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_clear_guest); void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); #ifdef CONFIG_HAVE_KVM_DIRTY_RING if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm)) return; WARN_ON_ONCE(!vcpu && !kvm_arch_allow_write_without_running_vcpu(kvm)); #endif if (memslot && kvm_slot_dirty_track_enabled(memslot)) { unsigned long rel_gfn = gfn - memslot->base_gfn; u32 slot = (memslot->as_id << 16) | memslot->id; if (kvm->dirty_ring_size && vcpu) kvm_dirty_ring_push(vcpu, slot, rel_gfn); else if (memslot->dirty_bitmap) set_bit_le(rel_gfn, memslot->dirty_bitmap); } } EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot); void mark_page_dirty(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot; memslot = gfn_to_memslot(kvm, gfn); mark_page_dirty_in_slot(kvm, memslot, gfn); } EXPORT_SYMBOL_GPL(mark_page_dirty); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memory_slot *memslot; memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); mark_page_dirty_in_slot(vcpu->kvm, memslot, gfn); } EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty); void kvm_sigset_activate(struct kvm_vcpu *vcpu) { if (!vcpu->sigset_active) return; /* * This does a lockless modification of ->real_blocked, which is fine * because, only current can change ->real_blocked and all readers of * ->real_blocked don't care as long ->real_blocked is always a subset * of ->blocked. */ sigprocmask(SIG_SETMASK, &vcpu->sigset, ¤t->real_blocked); } void kvm_sigset_deactivate(struct kvm_vcpu *vcpu) { if (!vcpu->sigset_active) return; sigprocmask(SIG_SETMASK, ¤t->real_blocked, NULL); sigemptyset(¤t->real_blocked); } static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) { unsigned int old, val, grow, grow_start; old = val = vcpu->halt_poll_ns; grow_start = READ_ONCE(halt_poll_ns_grow_start); grow = READ_ONCE(halt_poll_ns_grow); if (!grow) goto out; val *= grow; if (val < grow_start) val = grow_start; vcpu->halt_poll_ns = val; out: trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); } static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu) { unsigned int old, val, shrink, grow_start; old = val = vcpu->halt_poll_ns; shrink = READ_ONCE(halt_poll_ns_shrink); grow_start = READ_ONCE(halt_poll_ns_grow_start); if (shrink == 0) val = 0; else val /= shrink; if (val < grow_start) val = 0; vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old); } static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) { int ret = -EINTR; int idx = srcu_read_lock(&vcpu->kvm->srcu); if (kvm_arch_vcpu_runnable(vcpu)) goto out; if (kvm_cpu_has_pending_timer(vcpu)) goto out; if (signal_pending(current)) goto out; if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu)) goto out; ret = 0; out: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; } /* * Block the vCPU until the vCPU is runnable, an event arrives, or a signal is * pending. This is mostly used when halting a vCPU, but may also be used * directly for other vCPU non-runnable states, e.g. x86's Wait-For-SIPI. */ bool kvm_vcpu_block(struct kvm_vcpu *vcpu) { struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); bool waited = false; vcpu->stat.generic.blocking = 1; preempt_disable(); kvm_arch_vcpu_blocking(vcpu); prepare_to_rcuwait(wait); preempt_enable(); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (kvm_vcpu_check_block(vcpu) < 0) break; waited = true; schedule(); } preempt_disable(); finish_rcuwait(wait); kvm_arch_vcpu_unblocking(vcpu); preempt_enable(); vcpu->stat.generic.blocking = 0; return waited; } static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, ktime_t end, bool success) { struct kvm_vcpu_stat_generic *stats = &vcpu->stat.generic; u64 poll_ns = ktime_to_ns(ktime_sub(end, start)); ++vcpu->stat.generic.halt_attempted_poll; if (success) { ++vcpu->stat.generic.halt_successful_poll; if (!vcpu_valid_wakeup(vcpu)) ++vcpu->stat.generic.halt_poll_invalid; stats->halt_poll_success_ns += poll_ns; KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_success_hist, poll_ns); } else { stats->halt_poll_fail_ns += poll_ns; KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_fail_hist, poll_ns); } } static unsigned int kvm_vcpu_max_halt_poll_ns(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; if (kvm->override_halt_poll_ns) { /* * Ensure kvm->max_halt_poll_ns is not read before * kvm->override_halt_poll_ns. * * Pairs with the smp_wmb() when enabling KVM_CAP_HALT_POLL. */ smp_rmb(); return READ_ONCE(kvm->max_halt_poll_ns); } return READ_ONCE(halt_poll_ns); } /* * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt * polling is enabled, busy wait for a short time before blocking to avoid the * expensive block+unblock sequence if a wake event arrives soon after the vCPU * is halted. */ void kvm_vcpu_halt(struct kvm_vcpu *vcpu) { unsigned int max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); ktime_t start, cur, poll_end; bool waited = false; bool do_halt_poll; u64 halt_ns; if (vcpu->halt_poll_ns > max_halt_poll_ns) vcpu->halt_poll_ns = max_halt_poll_ns; do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; start = cur = poll_end = ktime_get(); if (do_halt_poll) { ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns); do { if (kvm_vcpu_check_block(vcpu) < 0) goto out; cpu_relax(); poll_end = cur = ktime_get(); } while (kvm_vcpu_can_poll(cur, stop)); } waited = kvm_vcpu_block(vcpu); cur = ktime_get(); if (waited) { vcpu->stat.generic.halt_wait_ns += ktime_to_ns(cur) - ktime_to_ns(poll_end); KVM_STATS_LOG_HIST_UPDATE(vcpu->stat.generic.halt_wait_hist, ktime_to_ns(cur) - ktime_to_ns(poll_end)); } out: /* The total time the vCPU was "halted", including polling time. */ halt_ns = ktime_to_ns(cur) - ktime_to_ns(start); /* * Note, halt-polling is considered successful so long as the vCPU was * never actually scheduled out, i.e. even if the wake event arrived * after of the halt-polling loop itself, but before the full wait. */ if (do_halt_poll) update_halt_poll_stats(vcpu, start, poll_end, !waited); if (halt_poll_allowed) { /* Recompute the max halt poll time in case it changed. */ max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); } else if (max_halt_poll_ns) { if (halt_ns <= vcpu->halt_poll_ns) ; /* we had a long block, shrink polling */ else if (vcpu->halt_poll_ns && halt_ns > max_halt_poll_ns) shrink_halt_poll_ns(vcpu); /* we had a short halt and our poll time is too small */ else if (vcpu->halt_poll_ns < max_halt_poll_ns && halt_ns < max_halt_poll_ns) grow_halt_poll_ns(vcpu); } else { vcpu->halt_poll_ns = 0; } } trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu)); } EXPORT_SYMBOL_GPL(kvm_vcpu_halt); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { if (__kvm_vcpu_wake_up(vcpu)) { WRITE_ONCE(vcpu->ready, true); ++vcpu->stat.generic.halt_wakeup; return true; } return false; } EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up); #ifndef CONFIG_S390 /* * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode. */ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { int me, cpu; if (kvm_vcpu_wake_up(vcpu)) return; me = get_cpu(); /* * The only state change done outside the vcpu mutex is IN_GUEST_MODE * to EXITING_GUEST_MODE. Therefore the moderately expensive "should * kick" check does not need atomic operations if kvm_vcpu_kick is used * within the vCPU thread itself. */ if (vcpu == __this_cpu_read(kvm_running_vcpu)) { if (vcpu->mode == IN_GUEST_MODE) WRITE_ONCE(vcpu->mode, EXITING_GUEST_MODE); goto out; } /* * Note, the vCPU could get migrated to a different pCPU at any point * after kvm_arch_vcpu_should_kick(), which could result in sending an * IPI to the previous pCPU. But, that's ok because the purpose of the * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the * vCPU also requires it to leave IN_GUEST_MODE. */ if (kvm_arch_vcpu_should_kick(vcpu)) { cpu = READ_ONCE(vcpu->cpu); if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); } out: put_cpu(); } EXPORT_SYMBOL_GPL(kvm_vcpu_kick); #endif /* !CONFIG_S390 */ int kvm_vcpu_yield_to(struct kvm_vcpu *target) { struct pid *pid; struct task_struct *task = NULL; int ret = 0; rcu_read_lock(); pid = rcu_dereference(target->pid); if (pid) task = get_pid_task(pid, PIDTYPE_PID); rcu_read_unlock(); if (!task) return ret; ret = yield_to(task, 1); put_task_struct(task); return ret; } EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to); /* * Helper that checks whether a VCPU is eligible for directed yield. * Most eligible candidate to yield is decided by following heuristics: * * (a) VCPU which has not done pl-exit or cpu relax intercepted recently * (preempted lock holder), indicated by @in_spin_loop. * Set at the beginning and cleared at the end of interception/PLE handler. * * (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get * chance last time (mostly it has become eligible now since we have probably * yielded to lockholder in last iteration. This is done by toggling * @dy_eligible each time a VCPU checked for eligibility.) * * Yielding to a recently pl-exited/cpu relax intercepted VCPU before yielding * to preempted lock-holder could result in wrong VCPU selection and CPU * burning. Giving priority for a potential lock-holder increases lock * progress. * * Since algorithm is based on heuristics, accessing another VCPU data without * locking does not harm. It may result in trying to yield to same VCPU, fail * and continue with next VCPU and so on. */ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) { #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT bool eligible; eligible = !vcpu->spin_loop.in_spin_loop || vcpu->spin_loop.dy_eligible; if (vcpu->spin_loop.in_spin_loop) kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible); return eligible; #else return true; #endif } /* * Unlike kvm_arch_vcpu_runnable, this function is called outside * a vcpu_load/vcpu_put pair. However, for most architectures * kvm_arch_vcpu_runnable does not require vcpu_load. */ bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) { return kvm_arch_vcpu_runnable(vcpu); } static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) { if (kvm_arch_dy_runnable(vcpu)) return true; #ifdef CONFIG_KVM_ASYNC_PF if (!list_empty_careful(&vcpu->async_pf.done)) return true; #endif return false; } /* * By default, simply query the target vCPU's current mode when checking if a * vCPU was preempted in kernel mode. All architectures except x86 (or more * specifical, except VMX) allow querying whether or not a vCPU is in kernel * mode even if the vCPU is NOT loaded, i.e. using kvm_arch_vcpu_in_kernel() * directly for cross-vCPU checks is functionally correct and accurate. */ bool __weak kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) { return kvm_arch_vcpu_in_kernel(vcpu); } bool __weak kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) { return false; } void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; int last_boosted_vcpu; unsigned long i; int yielded = 0; int try = 3; int pass; last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu); kvm_vcpu_set_in_spin_loop(me, true); /* * We boost the priority of a VCPU that is runnable but not * currently running, because it got preempted by something * else and called schedule in __vcpu_run. Hopefully that * VCPU is holding the lock that we need and will release it. * We approximate round-robin by starting at the last boosted VCPU. */ for (pass = 0; pass < 2 && !yielded && try; pass++) { kvm_for_each_vcpu(i, vcpu, kvm) { if (!pass && i <= last_boosted_vcpu) { i = last_boosted_vcpu; continue; } else if (pass && i > last_boosted_vcpu) break; if (!READ_ONCE(vcpu->ready)) continue; if (vcpu == me) continue; if (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu)) continue; /* * Treat the target vCPU as being in-kernel if it has a * pending interrupt, as the vCPU trying to yield may * be spinning waiting on IPI delivery, i.e. the target * vCPU is in-kernel for the purposes of directed yield. */ if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && !kvm_arch_dy_has_pending_interrupt(vcpu) && !kvm_arch_vcpu_preempted_in_kernel(vcpu)) continue; if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) continue; yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { WRITE_ONCE(kvm->last_boosted_vcpu, i); break; } else if (yielded < 0) { try--; if (!try) break; } } } kvm_vcpu_set_in_spin_loop(me, false); /* Ensure vcpu is not eligible during next spinloop */ kvm_vcpu_set_dy_eligible(me, false); } EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff) { #ifdef CONFIG_HAVE_KVM_DIRTY_RING return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) && (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET + kvm->dirty_ring_size / PAGE_SIZE); #else return false; #endif } static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf) { struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data; struct page *page; if (vmf->pgoff == 0) page = virt_to_page(vcpu->run); #ifdef CONFIG_X86 else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET) page = virt_to_page(vcpu->arch.pio_data); #endif #ifdef CONFIG_KVM_MMIO else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET) page = virt_to_page(vcpu->kvm->coalesced_mmio_ring); #endif else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff)) page = kvm_dirty_ring_get_page( &vcpu->dirty_ring, vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET); else return kvm_arch_vcpu_fault(vcpu, vmf); get_page(page); vmf->page = page; return 0; } static const struct vm_operations_struct kvm_vcpu_vm_ops = { .fault = kvm_vcpu_fault, }; static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma) { struct kvm_vcpu *vcpu = file->private_data; unsigned long pages = vma_pages(vma); if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) || kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) && ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED))) return -EINVAL; vma->vm_ops = &kvm_vcpu_vm_ops; return 0; } static int kvm_vcpu_release(struct inode *inode, struct file *filp) { struct kvm_vcpu *vcpu = filp->private_data; kvm_put_kvm(vcpu->kvm); return 0; } static struct file_operations kvm_vcpu_fops = { .release = kvm_vcpu_release, .unlocked_ioctl = kvm_vcpu_ioctl, .mmap = kvm_vcpu_mmap, .llseek = noop_llseek, KVM_COMPAT(kvm_vcpu_compat_ioctl), }; /* * Allocates an inode for the vcpu. */ static int create_vcpu_fd(struct kvm_vcpu *vcpu) { char name[8 + 1 + ITOA_MAX_LEN + 1]; snprintf(name, sizeof(name), "kvm-vcpu:%d", vcpu->vcpu_id); return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); } #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS static int vcpu_get_pid(void *data, u64 *val) { struct kvm_vcpu *vcpu = data; rcu_read_lock(); *val = pid_nr(rcu_dereference(vcpu->pid)); rcu_read_unlock(); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vcpu_get_pid_fops, vcpu_get_pid, NULL, "%llu\n"); static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) { struct dentry *debugfs_dentry; char dir_name[ITOA_MAX_LEN * 2]; if (!debugfs_initialized()) return; snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id); debugfs_dentry = debugfs_create_dir(dir_name, vcpu->kvm->debugfs_dentry); debugfs_create_file("pid", 0444, debugfs_dentry, vcpu, &vcpu_get_pid_fops); kvm_arch_create_vcpu_debugfs(vcpu, debugfs_dentry); } #endif /* * Creates some virtual cpus. Good luck creating more than one. */ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id) { int r; struct kvm_vcpu *vcpu; struct page *page; /* * KVM tracks vCPU IDs as 'int', be kind to userspace and reject * too-large values instead of silently truncating. * * Ensure KVM_MAX_VCPU_IDS isn't pushed above INT_MAX without first * changing the storage type (at the very least, IDs should be tracked * as unsigned ints). */ BUILD_BUG_ON(KVM_MAX_VCPU_IDS > INT_MAX); if (id >= KVM_MAX_VCPU_IDS) return -EINVAL; mutex_lock(&kvm->lock); if (kvm->created_vcpus >= kvm->max_vcpus) { mutex_unlock(&kvm->lock); return -EINVAL; } r = kvm_arch_vcpu_precreate(kvm, id); if (r) { mutex_unlock(&kvm->lock); return r; } kvm->created_vcpus++; mutex_unlock(&kvm->lock); vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); if (!vcpu) { r = -ENOMEM; goto vcpu_decrement; } BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE); page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) { r = -ENOMEM; goto vcpu_free; } vcpu->run = page_address(page); kvm_vcpu_init(vcpu, kvm, id); r = kvm_arch_vcpu_create(vcpu); if (r) goto vcpu_free_run_page; if (kvm->dirty_ring_size) { r = kvm_dirty_ring_alloc(&vcpu->dirty_ring, id, kvm->dirty_ring_size); if (r) goto arch_vcpu_destroy; } mutex_lock(&kvm->lock); #ifdef CONFIG_LOCKDEP /* Ensure that lockdep knows vcpu->mutex is taken *inside* kvm->lock */ mutex_lock(&vcpu->mutex); mutex_unlock(&vcpu->mutex); #endif if (kvm_get_vcpu_by_id(kvm, id)) { r = -EEXIST; goto unlock_vcpu_destroy; } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT); if (r) goto unlock_vcpu_destroy; /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) goto kvm_put_xa_release; if (KVM_BUG_ON(xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) { r = -EINVAL; goto kvm_put_xa_release; } /* * Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu * pointer before kvm->online_vcpu's incremented value. */ smp_wmb(); atomic_inc(&kvm->online_vcpus); mutex_unlock(&kvm->lock); kvm_arch_vcpu_postcreate(vcpu); kvm_create_vcpu_debugfs(vcpu); return r; kvm_put_xa_release: kvm_put_kvm_no_destroy(kvm); xa_release(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); kvm_dirty_ring_free(&vcpu->dirty_ring); arch_vcpu_destroy: kvm_arch_vcpu_destroy(vcpu); vcpu_free_run_page: free_page((unsigned long)vcpu->run); vcpu_free: kmem_cache_free(kvm_vcpu_cache, vcpu); vcpu_decrement: mutex_lock(&kvm->lock); kvm->created_vcpus--; mutex_unlock(&kvm->lock); return r; } static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) { if (sigset) { sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP)); vcpu->sigset_active = 1; vcpu->sigset = *sigset; } else vcpu->sigset_active = 0; return 0; } static ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer, size_t size, loff_t *offset) { struct kvm_vcpu *vcpu = file->private_data; return kvm_stats_read(vcpu->stats_id, &kvm_vcpu_stats_header, &kvm_vcpu_stats_desc[0], &vcpu->stat, sizeof(vcpu->stat), user_buffer, size, offset); } static int kvm_vcpu_stats_release(struct inode *inode, struct file *file) { struct kvm_vcpu *vcpu = file->private_data; kvm_put_kvm(vcpu->kvm); return 0; } static const struct file_operations kvm_vcpu_stats_fops = { .owner = THIS_MODULE, .read = kvm_vcpu_stats_read, .release = kvm_vcpu_stats_release, .llseek = noop_llseek, }; static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu) { int fd; struct file *file; char name[15 + ITOA_MAX_LEN + 1]; snprintf(name, sizeof(name), "kvm-vcpu-stats:%d", vcpu->vcpu_id); fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; file = anon_inode_getfile(name, &kvm_vcpu_stats_fops, vcpu, O_RDONLY); if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } kvm_get_kvm(vcpu->kvm); file->f_mode |= FMODE_PREAD; fd_install(fd, file); return fd; } #ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, struct kvm_pre_fault_memory *range) { int idx; long r; u64 full_size; if (range->flags) return -EINVAL; if (!PAGE_ALIGNED(range->gpa) || !PAGE_ALIGNED(range->size) || range->gpa + range->size <= range->gpa) return -EINVAL; vcpu_load(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); full_size = range->size; do { if (signal_pending(current)) { r = -EINTR; break; } r = kvm_arch_vcpu_pre_fault_memory(vcpu, range); if (WARN_ON_ONCE(r == 0 || r == -EIO)) break; if (r < 0) break; range->size -= r; range->gpa += r; cond_resched(); } while (range->size); srcu_read_unlock(&vcpu->kvm->srcu, idx); vcpu_put(vcpu); /* Return success if at least one page was mapped successfully. */ return full_size == range->size ? r : 0; } #endif static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; int r; struct kvm_fpu *fpu = NULL; struct kvm_sregs *kvm_sregs = NULL; if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) return -EINVAL; /* * Some architectures have vcpu ioctls that are asynchronous to vcpu * execution; mutex_lock() would break them. */ r = kvm_arch_vcpu_async_ioctl(filp, ioctl, arg); if (r != -ENOIOCTLCMD) return r; if (mutex_lock_killable(&vcpu->mutex)) return -EINTR; switch (ioctl) { case KVM_RUN: { struct pid *oldpid; r = -EINVAL; if (arg) goto out; oldpid = rcu_access_pointer(vcpu->pid); if (unlikely(oldpid != task_pid(current))) { /* The thread running this VCPU changed. */ struct pid *newpid; r = kvm_arch_vcpu_run_pid_change(vcpu); if (r) break; newpid = get_task_pid(current, PIDTYPE_PID); rcu_assign_pointer(vcpu->pid, newpid); if (oldpid) synchronize_rcu(); put_pid(oldpid); } vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe); r = kvm_arch_vcpu_ioctl_run(vcpu); vcpu->wants_to_run = false; trace_kvm_userspace_exit(vcpu->run->exit_reason, r); break; } case KVM_GET_REGS: { struct kvm_regs *kvm_regs; r = -ENOMEM; kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL); if (!kvm_regs) goto out; r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs); if (r) goto out_free1; r = -EFAULT; if (copy_to_user(argp, kvm_regs, sizeof(struct kvm_regs))) goto out_free1; r = 0; out_free1: kfree(kvm_regs); break; } case KVM_SET_REGS: { struct kvm_regs *kvm_regs; kvm_regs = memdup_user(argp, sizeof(*kvm_regs)); if (IS_ERR(kvm_regs)) { r = PTR_ERR(kvm_regs); goto out; } r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs); kfree(kvm_regs); break; } case KVM_GET_SREGS: { kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL); r = -ENOMEM; if (!kvm_sregs) goto out; r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, kvm_sregs); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, kvm_sregs, sizeof(struct kvm_sregs))) goto out; r = 0; break; } case KVM_SET_SREGS: { kvm_sregs = memdup_user(argp, sizeof(*kvm_sregs)); if (IS_ERR(kvm_sregs)) { r = PTR_ERR(kvm_sregs); kvm_sregs = NULL; goto out; } r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs); break; } case KVM_GET_MP_STATE: { struct kvm_mp_state mp_state; r = kvm_arch_vcpu_ioctl_get_mpstate(vcpu, &mp_state); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &mp_state, sizeof(mp_state))) goto out; r = 0; break; } case KVM_SET_MP_STATE: { struct kvm_mp_state mp_state; r = -EFAULT; if (copy_from_user(&mp_state, argp, sizeof(mp_state))) goto out; r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state); break; } case KVM_TRANSLATE: { struct kvm_translation tr; r = -EFAULT; if (copy_from_user(&tr, argp, sizeof(tr))) goto out; r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &tr, sizeof(tr))) goto out; r = 0; break; } case KVM_SET_GUEST_DEBUG: { struct kvm_guest_debug dbg; r = -EFAULT; if (copy_from_user(&dbg, argp, sizeof(dbg))) goto out; r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg); break; } case KVM_SET_SIGNAL_MASK: { struct kvm_signal_mask __user *sigmask_arg = argp; struct kvm_signal_mask kvm_sigmask; sigset_t sigset, *p; p = NULL; if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, sizeof(kvm_sigmask))) goto out; r = -EINVAL; if (kvm_sigmask.len != sizeof(sigset)) goto out; r = -EFAULT; if (copy_from_user(&sigset, sigmask_arg->sigset, sizeof(sigset))) goto out; p = &sigset; } r = kvm_vcpu_ioctl_set_sigmask(vcpu, p); break; } case KVM_GET_FPU: { fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL); r = -ENOMEM; if (!fpu) goto out; r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, fpu); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, fpu, sizeof(struct kvm_fpu))) goto out; r = 0; break; } case KVM_SET_FPU: { fpu = memdup_user(argp, sizeof(*fpu)); if (IS_ERR(fpu)) { r = PTR_ERR(fpu); fpu = NULL; goto out; } r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu); break; } case KVM_GET_STATS_FD: { r = kvm_vcpu_ioctl_get_stats_fd(vcpu); break; } #ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY case KVM_PRE_FAULT_MEMORY: { struct kvm_pre_fault_memory range; r = -EFAULT; if (copy_from_user(&range, argp, sizeof(range))) break; r = kvm_vcpu_pre_fault_memory(vcpu, &range); /* Pass back leftover range. */ if (copy_to_user(argp, &range, sizeof(range))) r = -EFAULT; break; } #endif default: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } out: mutex_unlock(&vcpu->mutex); kfree(fpu); kfree(kvm_sregs); return r; } #ifdef CONFIG_KVM_COMPAT static long kvm_vcpu_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = compat_ptr(arg); int r; if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_SET_SIGNAL_MASK: { struct kvm_signal_mask __user *sigmask_arg = argp; struct kvm_signal_mask kvm_sigmask; sigset_t sigset; if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, sizeof(kvm_sigmask))) goto out; r = -EINVAL; if (kvm_sigmask.len != sizeof(compat_sigset_t)) goto out; r = -EFAULT; if (get_compat_sigset(&sigset, (compat_sigset_t __user *)sigmask_arg->sigset)) goto out; r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); } else r = kvm_vcpu_ioctl_set_sigmask(vcpu, NULL); break; } default: r = kvm_vcpu_ioctl(filp, ioctl, arg); } out: return r; } #endif static int kvm_device_mmap(struct file *filp, struct vm_area_struct *vma) { struct kvm_device *dev = filp->private_data; if (dev->ops->mmap) return dev->ops->mmap(dev, vma); return -ENODEV; } static int kvm_device_ioctl_attr(struct kvm_device *dev, int (*accessor)(struct kvm_device *dev, struct kvm_device_attr *attr), unsigned long arg) { struct kvm_device_attr attr; if (!accessor) return -EPERM; if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) return -EFAULT; return accessor(dev, &attr); } static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_device *dev = filp->private_data; if (dev->kvm->mm != current->mm || dev->kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_SET_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg); case KVM_GET_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->get_attr, arg); case KVM_HAS_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->has_attr, arg); default: if (dev->ops->ioctl) return dev->ops->ioctl(dev, ioctl, arg); return -ENOTTY; } } static int kvm_device_release(struct inode *inode, struct file *filp) { struct kvm_device *dev = filp->private_data; struct kvm *kvm = dev->kvm; if (dev->ops->release) { mutex_lock(&kvm->lock); list_del_rcu(&dev->vm_node); synchronize_rcu(); dev->ops->release(dev); mutex_unlock(&kvm->lock); } kvm_put_kvm(kvm); return 0; } static struct file_operations kvm_device_fops = { .unlocked_ioctl = kvm_device_ioctl, .release = kvm_device_release, KVM_COMPAT(kvm_device_ioctl), .mmap = kvm_device_mmap, }; struct kvm_device *kvm_device_from_filp(struct file *filp) { if (filp->f_op != &kvm_device_fops) return NULL; return filp->private_data; } static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { #ifdef CONFIG_KVM_MPIC [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops, [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops, #endif }; int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type) { if (type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENOSPC; if (kvm_device_ops_table[type] != NULL) return -EEXIST; kvm_device_ops_table[type] = ops; return 0; } void kvm_unregister_device_ops(u32 type) { if (kvm_device_ops_table[type] != NULL) kvm_device_ops_table[type] = NULL; } static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_create_device *cd) { const struct kvm_device_ops *ops; struct kvm_device *dev; bool test = cd->flags & KVM_CREATE_DEVICE_TEST; int type; int ret; if (cd->type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENODEV; type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table)); ops = kvm_device_ops_table[type]; if (ops == NULL) return -ENODEV; if (test) return 0; dev = kzalloc(sizeof(*dev), GFP_KERNEL_ACCOUNT); if (!dev) return -ENOMEM; dev->ops = ops; dev->kvm = kvm; mutex_lock(&kvm->lock); ret = ops->create(dev, type); if (ret < 0) { mutex_unlock(&kvm->lock); kfree(dev); return ret; } list_add_rcu(&dev->vm_node, &kvm->devices); mutex_unlock(&kvm->lock); if (ops->init) ops->init(dev); kvm_get_kvm(kvm); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { kvm_put_kvm_no_destroy(kvm); mutex_lock(&kvm->lock); list_del_rcu(&dev->vm_node); synchronize_rcu(); if (ops->release) ops->release(dev); mutex_unlock(&kvm->lock); if (ops->destroy) ops->destroy(dev); return ret; } cd->fd = ret; return 0; } static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) { switch (arg) { case KVM_CAP_USER_MEMORY: case KVM_CAP_USER_MEMORY2: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: case KVM_CAP_INTERNAL_ERROR_DATA: #ifdef CONFIG_HAVE_KVM_MSI case KVM_CAP_SIGNAL_MSI: #endif #ifdef CONFIG_HAVE_KVM_IRQCHIP case KVM_CAP_IRQFD: #endif case KVM_CAP_IOEVENTFD_ANY_LENGTH: case KVM_CAP_CHECK_EXTENSION_VM: case KVM_CAP_ENABLE_CAP_VM: case KVM_CAP_HALT_POLL: return 1; #ifdef CONFIG_KVM_MMIO case KVM_CAP_COALESCED_MMIO: return KVM_COALESCED_MMIO_PAGE_OFFSET; case KVM_CAP_COALESCED_PIO: return 1; #endif #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: return KVM_DIRTY_LOG_MANUAL_CAPS; #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; #endif #if KVM_MAX_NR_ADDRESS_SPACES > 1 case KVM_CAP_MULTI_ADDRESS_SPACE: if (kvm) return kvm_arch_nr_memslot_as_ids(kvm); return KVM_MAX_NR_ADDRESS_SPACES; #endif case KVM_CAP_NR_MEMSLOTS: return KVM_USER_MEM_SLOTS; case KVM_CAP_DIRTY_LOG_RING: #ifdef CONFIG_HAVE_KVM_DIRTY_RING_TSO return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; #endif case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: #ifdef CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; #endif #ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: #endif case KVM_CAP_BINARY_STATS_FD: case KVM_CAP_SYSTEM_EVENT_DATA: case KVM_CAP_DEVICE_CTRL: return 1; #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES case KVM_CAP_MEMORY_ATTRIBUTES: return kvm_supported_mem_attributes(kvm); #endif #ifdef CONFIG_KVM_PRIVATE_MEM case KVM_CAP_GUEST_MEMFD: return !kvm || kvm_arch_has_private_mem(kvm); #endif default: break; } return kvm_vm_ioctl_check_extension(kvm, arg); } static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size) { int r; if (!KVM_DIRTY_LOG_PAGE_OFFSET) return -EINVAL; /* the size should be power of 2 */ if (!size || (size & (size - 1))) return -EINVAL; /* Should be bigger to keep the reserved entries, or a page */ if (size < kvm_dirty_ring_get_rsvd_entries() * sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE) return -EINVAL; if (size > KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn)) return -E2BIG; /* We only allow it to set once */ if (kvm->dirty_ring_size) return -EINVAL; mutex_lock(&kvm->lock); if (kvm->created_vcpus) { /* We don't allow to change this value after vcpu created */ r = -EINVAL; } else { kvm->dirty_ring_size = size; r = 0; } mutex_unlock(&kvm->lock); return r; } static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; int cleared = 0; if (!kvm->dirty_ring_size) return -EINVAL; mutex_lock(&kvm->slots_lock); kvm_for_each_vcpu(i, vcpu, kvm) cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring); mutex_unlock(&kvm->slots_lock); if (cleared) kvm_flush_remote_tlbs(kvm); return cleared; } int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { return -EINVAL; } bool kvm_are_all_memslots_empty(struct kvm *kvm) { int i; lockdep_assert_held(&kvm->slots_lock); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { if (!kvm_memslots_empty(__kvm_memslots(kvm, i))) return false; } return true; } EXPORT_SYMBOL_GPL(kvm_are_all_memslots_empty); static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, struct kvm_enable_cap *cap) { switch (cap->cap) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: { u64 allowed_options = KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE; if (cap->args[0] & KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE) allowed_options = KVM_DIRTY_LOG_MANUAL_CAPS; if (cap->flags || (cap->args[0] & ~allowed_options)) return -EINVAL; kvm->manual_dirty_log_protect = cap->args[0]; return 0; } #endif case KVM_CAP_HALT_POLL: { if (cap->flags || cap->args[0] != (unsigned int)cap->args[0]) return -EINVAL; kvm->max_halt_poll_ns = cap->args[0]; /* * Ensure kvm->override_halt_poll_ns does not become visible * before kvm->max_halt_poll_ns. * * Pairs with the smp_rmb() in kvm_vcpu_max_halt_poll_ns(). */ smp_wmb(); kvm->override_halt_poll_ns = true; return 0; } case KVM_CAP_DIRTY_LOG_RING: case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap)) return -EINVAL; return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]); case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: { int r = -EINVAL; if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) || !kvm->dirty_ring_size || cap->flags) return r; mutex_lock(&kvm->slots_lock); /* * For simplicity, allow enabling ring+bitmap if and only if * there are no memslots, e.g. to ensure all memslots allocate * a bitmap after the capability is enabled. */ if (kvm_are_all_memslots_empty(kvm)) { kvm->dirty_ring_with_bitmap = true; r = 0; } mutex_unlock(&kvm->slots_lock); return r; } default: return kvm_vm_ioctl_enable_cap(kvm, cap); } } static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer, size_t size, loff_t *offset) { struct kvm *kvm = file->private_data; return kvm_stats_read(kvm->stats_id, &kvm_vm_stats_header, &kvm_vm_stats_desc[0], &kvm->stat, sizeof(kvm->stat), user_buffer, size, offset); } static int kvm_vm_stats_release(struct inode *inode, struct file *file) { struct kvm *kvm = file->private_data; kvm_put_kvm(kvm); return 0; } static const struct file_operations kvm_vm_stats_fops = { .owner = THIS_MODULE, .read = kvm_vm_stats_read, .release = kvm_vm_stats_release, .llseek = noop_llseek, }; static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm) { int fd; struct file *file; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; file = anon_inode_getfile("kvm-vm-stats", &kvm_vm_stats_fops, kvm, O_RDONLY); if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } kvm_get_kvm(kvm); file->f_mode |= FMODE_PREAD; fd_install(fd, file); return fd; } #define SANITY_CHECK_MEM_REGION_FIELD(field) \ do { \ BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) != \ offsetof(struct kvm_userspace_memory_region2, field)); \ BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) != \ sizeof_field(struct kvm_userspace_memory_region2, field)); \ } while (0) static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; int r; if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: r = kvm_vm_ioctl_create_vcpu(kvm, arg); break; case KVM_ENABLE_CAP: { struct kvm_enable_cap cap; r = -EFAULT; if (copy_from_user(&cap, argp, sizeof(cap))) goto out; r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap); break; } case KVM_SET_USER_MEMORY_REGION2: case KVM_SET_USER_MEMORY_REGION: { struct kvm_userspace_memory_region2 mem; unsigned long size; if (ioctl == KVM_SET_USER_MEMORY_REGION) { /* * Fields beyond struct kvm_userspace_memory_region shouldn't be * accessed, but avoid leaking kernel memory in case of a bug. */ memset(&mem, 0, sizeof(mem)); size = sizeof(struct kvm_userspace_memory_region); } else { size = sizeof(struct kvm_userspace_memory_region2); } /* Ensure the common parts of the two structs are identical. */ SANITY_CHECK_MEM_REGION_FIELD(slot); SANITY_CHECK_MEM_REGION_FIELD(flags); SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr); SANITY_CHECK_MEM_REGION_FIELD(memory_size); SANITY_CHECK_MEM_REGION_FIELD(userspace_addr); r = -EFAULT; if (copy_from_user(&mem, argp, size)) goto out; r = -EINVAL; if (ioctl == KVM_SET_USER_MEMORY_REGION && (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS)) goto out; r = kvm_vm_ioctl_set_memory_region(kvm, &mem); break; } case KVM_GET_DIRTY_LOG: { struct kvm_dirty_log log; r = -EFAULT; if (copy_from_user(&log, argp, sizeof(log))) goto out; r = kvm_vm_ioctl_get_dirty_log(kvm, &log); break; } #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CLEAR_DIRTY_LOG: { struct kvm_clear_dirty_log log; r = -EFAULT; if (copy_from_user(&log, argp, sizeof(log))) goto out; r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); break; } #endif #ifdef CONFIG_KVM_MMIO case KVM_REGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; r = -EFAULT; if (copy_from_user(&zone, argp, sizeof(zone))) goto out; r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone); break; } case KVM_UNREGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; r = -EFAULT; if (copy_from_user(&zone, argp, sizeof(zone))) goto out; r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone); break; } #endif case KVM_IRQFD: { struct kvm_irqfd data; r = -EFAULT; if (copy_from_user(&data, argp, sizeof(data))) goto out; r = kvm_irqfd(kvm, &data); break; } case KVM_IOEVENTFD: { struct kvm_ioeventfd data; r = -EFAULT; if (copy_from_user(&data, argp, sizeof(data))) goto out; r = kvm_ioeventfd(kvm, &data); break; } #ifdef CONFIG_HAVE_KVM_MSI case KVM_SIGNAL_MSI: { struct kvm_msi msi; r = -EFAULT; if (copy_from_user(&msi, argp, sizeof(msi))) goto out; r = kvm_send_userspace_msi(kvm, &msi); break; } #endif #ifdef __KVM_HAVE_IRQ_LINE case KVM_IRQ_LINE_STATUS: case KVM_IRQ_LINE: { struct kvm_irq_level irq_event; r = -EFAULT; if (copy_from_user(&irq_event, argp, sizeof(irq_event))) goto out; r = kvm_vm_ioctl_irq_line(kvm, &irq_event, ioctl == KVM_IRQ_LINE_STATUS); if (r) goto out; r = -EFAULT; if (ioctl == KVM_IRQ_LINE_STATUS) { if (copy_to_user(argp, &irq_event, sizeof(irq_event))) goto out; } r = 0; break; } #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_SET_GSI_ROUTING: { struct kvm_irq_routing routing; struct kvm_irq_routing __user *urouting; struct kvm_irq_routing_entry *entries = NULL; r = -EFAULT; if (copy_from_user(&routing, argp, sizeof(routing))) goto out; r = -EINVAL; if (!kvm_arch_can_set_irq_routing(kvm)) goto out; if (routing.nr > KVM_MAX_IRQ_ROUTES) goto out; if (routing.flags) goto out; if (routing.nr) { urouting = argp; entries = vmemdup_array_user(urouting->entries, routing.nr, sizeof(*entries)); if (IS_ERR(entries)) { r = PTR_ERR(entries); goto out; } } r = kvm_set_irq_routing(kvm, entries, routing.nr, routing.flags); kvfree(entries); break; } #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES case KVM_SET_MEMORY_ATTRIBUTES: { struct kvm_memory_attributes attrs; r = -EFAULT; if (copy_from_user(&attrs, argp, sizeof(attrs))) goto out; r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs); break; } #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ case KVM_CREATE_DEVICE: { struct kvm_create_device cd; r = -EFAULT; if (copy_from_user(&cd, argp, sizeof(cd))) goto out; r = kvm_ioctl_create_device(kvm, &cd); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &cd, sizeof(cd))) goto out; r = 0; break; } case KVM_CHECK_EXTENSION: r = kvm_vm_ioctl_check_extension_generic(kvm, arg); break; case KVM_RESET_DIRTY_RINGS: r = kvm_vm_ioctl_reset_dirty_pages(kvm); break; case KVM_GET_STATS_FD: r = kvm_vm_ioctl_get_stats_fd(kvm); break; #ifdef CONFIG_KVM_PRIVATE_MEM case KVM_CREATE_GUEST_MEMFD: { struct kvm_create_guest_memfd guest_memfd; r = -EFAULT; if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd))) goto out; r = kvm_gmem_create(kvm, &guest_memfd); break; } #endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } out: return r; } #ifdef CONFIG_KVM_COMPAT struct compat_kvm_dirty_log { __u32 slot; __u32 padding1; union { compat_uptr_t dirty_bitmap; /* one bit per page */ __u64 padding2; }; }; struct compat_kvm_clear_dirty_log { __u32 slot; __u32 num_pages; __u64 first_page; union { compat_uptr_t dirty_bitmap; /* one bit per page */ __u64 padding2; }; }; long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -ENOTTY; } static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; int r; if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg); if (r != -ENOTTY) return r; switch (ioctl) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CLEAR_DIRTY_LOG: { struct compat_kvm_clear_dirty_log compat_log; struct kvm_clear_dirty_log log; if (copy_from_user(&compat_log, (void __user *)arg, sizeof(compat_log))) return -EFAULT; log.slot = compat_log.slot; log.num_pages = compat_log.num_pages; log.first_page = compat_log.first_page; log.padding2 = compat_log.padding2; log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); break; } #endif case KVM_GET_DIRTY_LOG: { struct compat_kvm_dirty_log compat_log; struct kvm_dirty_log log; if (copy_from_user(&compat_log, (void __user *)arg, sizeof(compat_log))) return -EFAULT; log.slot = compat_log.slot; log.padding1 = compat_log.padding1; log.padding2 = compat_log.padding2; log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); r = kvm_vm_ioctl_get_dirty_log(kvm, &log); break; } default: r = kvm_vm_ioctl(filp, ioctl, arg); } return r; } #endif static struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, .llseek = noop_llseek, KVM_COMPAT(kvm_vm_compat_ioctl), }; bool file_is_kvm(struct file *file) { return file && file->f_op == &kvm_vm_fops; } EXPORT_SYMBOL_GPL(file_is_kvm); static int kvm_dev_ioctl_create_vm(unsigned long type) { char fdname[ITOA_MAX_LEN + 1]; int r, fd; struct kvm *kvm; struct file *file; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; snprintf(fdname, sizeof(fdname), "%d", fd); kvm = kvm_create_vm(type, fdname); if (IS_ERR(kvm)) { r = PTR_ERR(kvm); goto put_fd; } file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); if (IS_ERR(file)) { r = PTR_ERR(file); goto put_kvm; } /* * Don't call kvm_put_kvm anymore at this point; file->f_op is * already set, with ->release() being kvm_vm_release(). In error * cases it will be called by the final fput(file) and will take * care of doing kvm_put_kvm(kvm). */ kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm); fd_install(fd, file); return fd; put_kvm: kvm_put_kvm(kvm); put_fd: put_unused_fd(fd); return r; } static long kvm_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { int r = -EINVAL; switch (ioctl) { case KVM_GET_API_VERSION: if (arg) goto out; r = KVM_API_VERSION; break; case KVM_CREATE_VM: r = kvm_dev_ioctl_create_vm(arg); break; case KVM_CHECK_EXTENSION: r = kvm_vm_ioctl_check_extension_generic(NULL, arg); break; case KVM_GET_VCPU_MMAP_SIZE: if (arg) goto out; r = PAGE_SIZE; /* struct kvm_run */ #ifdef CONFIG_X86 r += PAGE_SIZE; /* pio data page */ #endif #ifdef CONFIG_KVM_MMIO r += PAGE_SIZE; /* coalesced mmio ring page */ #endif break; default: return kvm_arch_dev_ioctl(filp, ioctl, arg); } out: return r; } static struct file_operations kvm_chardev_ops = { .unlocked_ioctl = kvm_dev_ioctl, .llseek = noop_llseek, KVM_COMPAT(kvm_dev_ioctl), }; static struct miscdevice kvm_dev = { KVM_MINOR, "kvm", &kvm_chardev_ops, }; #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); static DEFINE_PER_CPU(bool, hardware_enabled); static int kvm_usage_count; static int __hardware_enable_nolock(void) { if (__this_cpu_read(hardware_enabled)) return 0; if (kvm_arch_hardware_enable()) { pr_info("kvm: enabling virtualization on CPU%d failed\n", raw_smp_processor_id()); return -EIO; } __this_cpu_write(hardware_enabled, true); return 0; } static void hardware_enable_nolock(void *failed) { if (__hardware_enable_nolock()) atomic_inc(failed); } static int kvm_online_cpu(unsigned int cpu) { int ret = 0; /* * Abort the CPU online process if hardware virtualization cannot * be enabled. Otherwise running VMs would encounter unrecoverable * errors when scheduled to this CPU. */ mutex_lock(&kvm_lock); if (kvm_usage_count) ret = __hardware_enable_nolock(); mutex_unlock(&kvm_lock); return ret; } static void hardware_disable_nolock(void *junk) { /* * Note, hardware_disable_all_nolock() tells all online CPUs to disable * hardware, not just CPUs that successfully enabled hardware! */ if (!__this_cpu_read(hardware_enabled)) return; kvm_arch_hardware_disable(); __this_cpu_write(hardware_enabled, false); } static int kvm_offline_cpu(unsigned int cpu) { mutex_lock(&kvm_lock); if (kvm_usage_count) hardware_disable_nolock(NULL); mutex_unlock(&kvm_lock); return 0; } static void hardware_disable_all_nolock(void) { BUG_ON(!kvm_usage_count); kvm_usage_count--; if (!kvm_usage_count) on_each_cpu(hardware_disable_nolock, NULL, 1); } static void hardware_disable_all(void) { cpus_read_lock(); mutex_lock(&kvm_lock); hardware_disable_all_nolock(); mutex_unlock(&kvm_lock); cpus_read_unlock(); } static int hardware_enable_all(void) { atomic_t failed = ATOMIC_INIT(0); int r; /* * Do not enable hardware virtualization if the system is going down. * If userspace initiated a forced reboot, e.g. reboot -f, then it's * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling * after kvm_reboot() is called. Note, this relies on system_state * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops * hook instead of registering a dedicated reboot notifier (the latter * runs before system_state is updated). */ if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || system_state == SYSTEM_RESTART) return -EBUSY; /* * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() * is called, and so on_each_cpu() between them includes the CPU that * is being onlined. As a result, hardware_enable_nolock() may get * invoked before kvm_online_cpu(), which also enables hardware if the * usage count is non-zero. Disable CPU hotplug to avoid attempting to * enable hardware multiple times. */ cpus_read_lock(); mutex_lock(&kvm_lock); r = 0; kvm_usage_count++; if (kvm_usage_count == 1) { on_each_cpu(hardware_enable_nolock, &failed, 1); if (atomic_read(&failed)) { hardware_disable_all_nolock(); r = -EBUSY; } } mutex_unlock(&kvm_lock); cpus_read_unlock(); return r; } static void kvm_shutdown(void) { /* * Disable hardware virtualization and set kvm_rebooting to indicate * that KVM has asynchronously disabled hardware virtualization, i.e. * that relevant errors and exceptions aren't entirely unexpected. * Some flavors of hardware virtualization need to be disabled before * transferring control to firmware (to perform shutdown/reboot), e.g. * on x86, virtualization can block INIT interrupts, which are used by * firmware to pull APs back under firmware control. Note, this path * is used for both shutdown and reboot scenarios, i.e. neither name is * 100% comprehensive. */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(hardware_disable_nolock, NULL, 1); } static int kvm_suspend(void) { /* * Secondary CPUs and CPU hotplug are disabled across the suspend/resume * callbacks, i.e. no need to acquire kvm_lock to ensure the usage count * is stable. Assert that kvm_lock is not held to ensure the system * isn't suspended while KVM is enabling hardware. Hardware enabling * can be preempted, but the task cannot be frozen until it has dropped * all locks (userspace tasks are frozen via a fake signal). */ lockdep_assert_not_held(&kvm_lock); lockdep_assert_irqs_disabled(); if (kvm_usage_count) hardware_disable_nolock(NULL); return 0; } static void kvm_resume(void) { lockdep_assert_not_held(&kvm_lock); lockdep_assert_irqs_disabled(); if (kvm_usage_count) WARN_ON_ONCE(__hardware_enable_nolock()); } static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, .shutdown = kvm_shutdown, }; #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static int hardware_enable_all(void) { return 0; } static void hardware_disable_all(void) { } #endif /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static void kvm_iodevice_destructor(struct kvm_io_device *dev) { if (dev->ops->destructor) dev->ops->destructor(dev); } static void kvm_io_bus_destroy(struct kvm_io_bus *bus) { int i; for (i = 0; i < bus->dev_count; i++) { struct kvm_io_device *pos = bus->range[i].dev; kvm_iodevice_destructor(pos); } kfree(bus); } static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1, const struct kvm_io_range *r2) { gpa_t addr1 = r1->addr; gpa_t addr2 = r2->addr; if (addr1 < addr2) return -1; /* If r2->len == 0, match the exact address. If r2->len != 0, * accept any overlapping write. Any order is acceptable for * overlapping ranges, because kvm_io_bus_get_first_dev ensures * we process all of them. */ if (r2->len) { addr1 += r1->len; addr2 += r2->len; } if (addr1 > addr2) return 1; return 0; } static int kvm_io_bus_sort_cmp(const void *p1, const void *p2) { return kvm_io_bus_cmp(p1, p2); } static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus, gpa_t addr, int len) { struct kvm_io_range *range, key; int off; key = (struct kvm_io_range) { .addr = addr, .len = len, }; range = bsearch(&key, bus->range, bus->dev_count, sizeof(struct kvm_io_range), kvm_io_bus_sort_cmp); if (range == NULL) return -ENOENT; off = range - bus->range; while (off > 0 && kvm_io_bus_cmp(&key, &bus->range[off-1]) == 0) off--; return off; } static int __kvm_io_bus_write(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus, struct kvm_io_range *range, const void *val) { int idx; idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); if (idx < 0) return -EOPNOTSUPP; while (idx < bus->dev_count && kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { if (!kvm_iodevice_write(vcpu, bus->range[idx].dev, range->addr, range->len, val)) return idx; idx++; } return -EOPNOTSUPP; } /* kvm_io_bus_write - called under kvm->slots_lock */ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { struct kvm_io_bus *bus; struct kvm_io_range range; int r; range = (struct kvm_io_range) { .addr = addr, .len = len, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus) return -ENOMEM; r = __kvm_io_bus_write(vcpu, bus, &range, val); return r < 0 ? r : 0; } EXPORT_SYMBOL_GPL(kvm_io_bus_write); /* kvm_io_bus_write_cookie - called under kvm->slots_lock */ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val, long cookie) { struct kvm_io_bus *bus; struct kvm_io_range range; range = (struct kvm_io_range) { .addr = addr, .len = len, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus) return -ENOMEM; /* First try the device referenced by cookie. */ if ((cookie >= 0) && (cookie < bus->dev_count) && (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0)) if (!kvm_iodevice_write(vcpu, bus->range[cookie].dev, addr, len, val)) return cookie; /* * cookie contained garbage; fall back to search and return the * correct cookie value. */ return __kvm_io_bus_write(vcpu, bus, &range, val); } static int __kvm_io_bus_read(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus, struct kvm_io_range *range, void *val) { int idx; idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); if (idx < 0) return -EOPNOTSUPP; while (idx < bus->dev_count && kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { if (!kvm_iodevice_read(vcpu, bus->range[idx].dev, range->addr, range->len, val)) return idx; idx++; } return -EOPNOTSUPP; } /* kvm_io_bus_read - called under kvm->slots_lock */ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val) { struct kvm_io_bus *bus; struct kvm_io_range range; int r; range = (struct kvm_io_range) { .addr = addr, .len = len, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus) return -ENOMEM; r = __kvm_io_bus_read(vcpu, bus, &range, val); return r < 0 ? r : 0; } int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev) { int i; struct kvm_io_bus *new_bus, *bus; struct kvm_io_range range; lockdep_assert_held(&kvm->slots_lock); bus = kvm_get_bus(kvm, bus_idx); if (!bus) return -ENOMEM; /* exclude ioeventfd which is limited by maximum fd */ if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1) return -ENOSPC; new_bus = kmalloc(struct_size(bus, range, bus->dev_count + 1), GFP_KERNEL_ACCOUNT); if (!new_bus) return -ENOMEM; range = (struct kvm_io_range) { .addr = addr, .len = len, .dev = dev, }; for (i = 0; i < bus->dev_count; i++) if (kvm_io_bus_cmp(&bus->range[i], &range) > 0) break; memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); new_bus->dev_count++; new_bus->range[i] = range; memcpy(new_bus->range + i + 1, bus->range + i, (bus->dev_count - i) * sizeof(struct kvm_io_range)); rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); kfree(bus); return 0; } int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev) { int i; struct kvm_io_bus *new_bus, *bus; lockdep_assert_held(&kvm->slots_lock); bus = kvm_get_bus(kvm, bus_idx); if (!bus) return 0; for (i = 0; i < bus->dev_count; i++) { if (bus->range[i].dev == dev) { break; } } if (i == bus->dev_count) return 0; new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1), GFP_KERNEL_ACCOUNT); if (new_bus) { memcpy(new_bus, bus, struct_size(bus, range, i)); new_bus->dev_count--; memcpy(new_bus->range + i, bus->range + i + 1, flex_array_size(new_bus, range, new_bus->dev_count - i)); } rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); /* * If NULL bus is installed, destroy the old bus, including all the * attached devices. Otherwise, destroy the caller's device only. */ if (!new_bus) { pr_err("kvm: failed to shrink bus, removing it completely\n"); kvm_io_bus_destroy(bus); return -ENOMEM; } kvm_iodevice_destructor(dev); kfree(bus); return 0; } struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr) { struct kvm_io_bus *bus; int dev_idx, srcu_idx; struct kvm_io_device *iodev = NULL; srcu_idx = srcu_read_lock(&kvm->srcu); bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); if (!bus) goto out_unlock; dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1); if (dev_idx < 0) goto out_unlock; iodev = bus->range[dev_idx].dev; out_unlock: srcu_read_unlock(&kvm->srcu, srcu_idx); return iodev; } EXPORT_SYMBOL_GPL(kvm_io_bus_get_dev); static int kvm_debugfs_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt) { int ret; struct kvm_stat_data *stat_data = inode->i_private; /* * The debugfs files are a reference to the kvm struct which * is still valid when kvm_destroy_vm is called. kvm_get_kvm_safe * avoids the race between open and the removal of the debugfs directory. */ if (!kvm_get_kvm_safe(stat_data->kvm)) return -ENOENT; ret = simple_attr_open(inode, file, get, kvm_stats_debugfs_mode(stat_data->desc) & 0222 ? set : NULL, fmt); if (ret) kvm_put_kvm(stat_data->kvm); return ret; } static int kvm_debugfs_release(struct inode *inode, struct file *file) { struct kvm_stat_data *stat_data = inode->i_private; simple_attr_release(inode, file); kvm_put_kvm(stat_data->kvm); return 0; } static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val) { *val = *(u64 *)((void *)(&kvm->stat) + offset); return 0; } static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) { *(u64 *)((void *)(&kvm->stat) + offset) = 0; return 0; } static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) { unsigned long i; struct kvm_vcpu *vcpu; *val = 0; kvm_for_each_vcpu(i, vcpu, kvm) *val += *(u64 *)((void *)(&vcpu->stat) + offset); return 0; } static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) *(u64 *)((void *)(&vcpu->stat) + offset) = 0; return 0; } static int kvm_stat_data_get(void *data, u64 *val) { int r = -EFAULT; struct kvm_stat_data *stat_data = data; switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_get_stat_per_vm(stat_data->kvm, stat_data->desc->desc.offset, val); break; case KVM_STAT_VCPU: r = kvm_get_stat_per_vcpu(stat_data->kvm, stat_data->desc->desc.offset, val); break; } return r; } static int kvm_stat_data_clear(void *data, u64 val) { int r = -EFAULT; struct kvm_stat_data *stat_data = data; if (val) return -EINVAL; switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_clear_stat_per_vm(stat_data->kvm, stat_data->desc->desc.offset); break; case KVM_STAT_VCPU: r = kvm_clear_stat_per_vcpu(stat_data->kvm, stat_data->desc->desc.offset); break; } return r; } static int kvm_stat_data_open(struct inode *inode, struct file *file) { __simple_attr_check_format("%llu\n", 0ull); return kvm_debugfs_open(inode, file, kvm_stat_data_get, kvm_stat_data_clear, "%llu\n"); } static const struct file_operations stat_fops_per_vm = { .owner = THIS_MODULE, .open = kvm_stat_data_open, .release = kvm_debugfs_release, .read = simple_attr_read, .write = simple_attr_write, .llseek = no_llseek, }; static int vm_stat_get(void *_offset, u64 *val) { unsigned offset = (long)_offset; struct kvm *kvm; u64 tmp_val; *val = 0; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_get_stat_per_vm(kvm, offset, &tmp_val); *val += tmp_val; } mutex_unlock(&kvm_lock); return 0; } static int vm_stat_clear(void *_offset, u64 val) { unsigned offset = (long)_offset; struct kvm *kvm; if (val) return -EINVAL; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_clear_stat_per_vm(kvm, offset); } mutex_unlock(&kvm_lock); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n"); DEFINE_SIMPLE_ATTRIBUTE(vm_stat_readonly_fops, vm_stat_get, NULL, "%llu\n"); static int vcpu_stat_get(void *_offset, u64 *val) { unsigned offset = (long)_offset; struct kvm *kvm; u64 tmp_val; *val = 0; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_get_stat_per_vcpu(kvm, offset, &tmp_val); *val += tmp_val; } mutex_unlock(&kvm_lock); return 0; } static int vcpu_stat_clear(void *_offset, u64 val) { unsigned offset = (long)_offset; struct kvm *kvm; if (val) return -EINVAL; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_clear_stat_per_vcpu(kvm, offset); } mutex_unlock(&kvm_lock); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear, "%llu\n"); DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_readonly_fops, vcpu_stat_get, NULL, "%llu\n"); static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) { struct kobj_uevent_env *env; unsigned long long created, active; if (!kvm_dev.this_device || !kvm) return; mutex_lock(&kvm_lock); if (type == KVM_EVENT_CREATE_VM) { kvm_createvm_count++; kvm_active_vms++; } else if (type == KVM_EVENT_DESTROY_VM) { kvm_active_vms--; } created = kvm_createvm_count; active = kvm_active_vms; mutex_unlock(&kvm_lock); env = kzalloc(sizeof(*env), GFP_KERNEL); if (!env) return; add_uevent_var(env, "CREATED=%llu", created); add_uevent_var(env, "COUNT=%llu", active); if (type == KVM_EVENT_CREATE_VM) { add_uevent_var(env, "EVENT=create"); kvm->userspace_pid = task_pid_nr(current); } else if (type == KVM_EVENT_DESTROY_VM) { add_uevent_var(env, "EVENT=destroy"); } add_uevent_var(env, "PID=%d", kvm->userspace_pid); if (!IS_ERR(kvm->debugfs_dentry)) { char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL); if (p) { tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX); if (!IS_ERR(tmp)) add_uevent_var(env, "STATS_PATH=%s", tmp); kfree(p); } } /* no need for checks, since we are adding at most only 5 keys */ env->envp[env->envp_idx++] = NULL; kobject_uevent_env(&kvm_dev.this_device->kobj, KOBJ_CHANGE, env->envp); kfree(env); } static void kvm_init_debug(void) { const struct file_operations *fops; const struct _kvm_stats_desc *pdesc; int i; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { pdesc = &kvm_vm_stats_desc[i]; if (kvm_stats_debugfs_mode(pdesc) & 0222) fops = &vm_stat_fops; else fops = &vm_stat_readonly_fops; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm_debugfs_dir, (void *)(long)pdesc->desc.offset, fops); } for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { pdesc = &kvm_vcpu_stats_desc[i]; if (kvm_stats_debugfs_mode(pdesc) & 0222) fops = &vcpu_stat_fops; else fops = &vcpu_stat_readonly_fops; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm_debugfs_dir, (void *)(long)pdesc->desc.offset, fops); } } static inline struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) { return container_of(pn, struct kvm_vcpu, preempt_notifier); } static void kvm_sched_in(struct preempt_notifier *pn, int cpu) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); WRITE_ONCE(vcpu->preempted, false); WRITE_ONCE(vcpu->ready, false); __this_cpu_write(kvm_running_vcpu, vcpu); kvm_arch_vcpu_load(vcpu, cpu); WRITE_ONCE(vcpu->scheduled_out, false); } static void kvm_sched_out(struct preempt_notifier *pn, struct task_struct *next) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); WRITE_ONCE(vcpu->scheduled_out, true); if (current->on_rq && vcpu->wants_to_run) { WRITE_ONCE(vcpu->preempted, true); WRITE_ONCE(vcpu->ready, true); } kvm_arch_vcpu_put(vcpu); __this_cpu_write(kvm_running_vcpu, NULL); } /** * kvm_get_running_vcpu - get the vcpu running on the current CPU. * * We can disable preemption locally around accessing the per-CPU variable, * and use the resolved vcpu pointer after enabling preemption again, * because even if the current thread is migrated to another CPU, reading * the per-CPU value later will give us the same value as we update the * per-CPU variable in the preempt notifier handlers. */ struct kvm_vcpu *kvm_get_running_vcpu(void) { struct kvm_vcpu *vcpu; preempt_disable(); vcpu = __this_cpu_read(kvm_running_vcpu); preempt_enable(); return vcpu; } EXPORT_SYMBOL_GPL(kvm_get_running_vcpu); /** * kvm_get_running_vcpus - get the per-CPU array of currently running vcpus. */ struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) { return &kvm_running_vcpu; } #ifdef CONFIG_GUEST_PERF_EVENTS static unsigned int kvm_guest_state(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); unsigned int state; if (!kvm_arch_pmi_in_guest(vcpu)) return 0; state = PERF_GUEST_ACTIVE; if (!kvm_arch_vcpu_in_kernel(vcpu)) state |= PERF_GUEST_USER; return state; } static unsigned long kvm_guest_get_ip(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); /* Retrieving the IP must be guarded by a call to kvm_guest_state(). */ if (WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu))) return 0; return kvm_arch_vcpu_get_ip(vcpu); } static struct perf_guest_info_callbacks kvm_guest_cbs = { .state = kvm_guest_state, .get_ip = kvm_guest_get_ip, .handle_intel_pt_intr = NULL, }; void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)) { kvm_guest_cbs.handle_intel_pt_intr = pt_intr_handler; perf_register_guest_info_callbacks(&kvm_guest_cbs); } void kvm_unregister_perf_callbacks(void) { perf_unregister_guest_info_callbacks(&kvm_guest_cbs); } #endif int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) { int r; int cpu; #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", kvm_online_cpu, kvm_offline_cpu); if (r) return r; register_syscore_ops(&kvm_syscore_ops); #endif /* A kmem cache lets us meet the alignment requirements of fx_save. */ if (!vcpu_align) vcpu_align = __alignof__(struct kvm_vcpu); kvm_vcpu_cache = kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align, SLAB_ACCOUNT, offsetof(struct kvm_vcpu, arch), offsetofend(struct kvm_vcpu, stats_id) - offsetof(struct kvm_vcpu, arch), NULL); if (!kvm_vcpu_cache) { r = -ENOMEM; goto err_vcpu_cache; } for_each_possible_cpu(cpu) { if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), GFP_KERNEL, cpu_to_node(cpu))) { r = -ENOMEM; goto err_cpu_kick_mask; } } r = kvm_irqfd_init(); if (r) goto err_irqfd; r = kvm_async_pf_init(); if (r) goto err_async_pf; kvm_chardev_ops.owner = module; kvm_vm_fops.owner = module; kvm_vcpu_fops.owner = module; kvm_device_fops.owner = module; kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; kvm_init_debug(); r = kvm_vfio_ops_init(); if (WARN_ON_ONCE(r)) goto err_vfio; kvm_gmem_init(module); /* * Registration _must_ be the very last thing done, as this exposes * /dev/kvm to userspace, i.e. all infrastructure must be setup! */ r = misc_register(&kvm_dev); if (r) { pr_err("kvm: misc device register failed\n"); goto err_register; } return 0; err_register: kvm_vfio_ops_exit(); err_vfio: kvm_async_pf_deinit(); err_async_pf: kvm_irqfd_exit(); err_irqfd: err_cpu_kick_mask: for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); err_vcpu_cache: #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif return r; } EXPORT_SYMBOL_GPL(kvm_init); void kvm_exit(void) { int cpu; /* * Note, unregistering /dev/kvm doesn't strictly need to come first, * fops_get(), a.k.a. try_module_get(), prevents acquiring references * to KVM while the module is being stopped. */ misc_deregister(&kvm_dev); debugfs_remove_recursive(kvm_debugfs_dir); for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); kvm_vfio_ops_exit(); kvm_async_pf_deinit(); #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif kvm_irqfd_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); struct kvm_vm_worker_thread_context { struct kvm *kvm; struct task_struct *parent; struct completion init_done; kvm_vm_thread_fn_t thread_fn; uintptr_t data; int err; }; static int kvm_vm_worker_thread(void *context) { /* * The init_context is allocated on the stack of the parent thread, so * we have to locally copy anything that is needed beyond initialization */ struct kvm_vm_worker_thread_context *init_context = context; struct task_struct *parent; struct kvm *kvm = init_context->kvm; kvm_vm_thread_fn_t thread_fn = init_context->thread_fn; uintptr_t data = init_context->data; int err; err = kthread_park(current); /* kthread_park(current) is never supposed to return an error */ WARN_ON(err != 0); if (err) goto init_complete; err = cgroup_attach_task_all(init_context->parent, current); if (err) { kvm_err("%s: cgroup_attach_task_all failed with err %d\n", __func__, err); goto init_complete; } set_user_nice(current, task_nice(init_context->parent)); init_complete: init_context->err = err; complete(&init_context->init_done); init_context = NULL; if (err) goto out; /* Wait to be woken up by the spawner before proceeding. */ kthread_parkme(); if (!kthread_should_stop()) err = thread_fn(kvm, data); out: /* * Move kthread back to its original cgroup to prevent it lingering in * the cgroup of the VM process, after the latter finishes its * execution. * * kthread_stop() waits on the 'exited' completion condition which is * set in exit_mm(), via mm_release(), in do_exit(). However, the * kthread is removed from the cgroup in the cgroup_exit() which is * called after the exit_mm(). This causes the kthread_stop() to return * before the kthread actually quits the cgroup. */ rcu_read_lock(); parent = rcu_dereference(current->real_parent); get_task_struct(parent); rcu_read_unlock(); cgroup_attach_task_all(parent, current); put_task_struct(parent); return err; } int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, uintptr_t data, const char *name, struct task_struct **thread_ptr) { struct kvm_vm_worker_thread_context init_context = {}; struct task_struct *thread; *thread_ptr = NULL; init_context.kvm = kvm; init_context.parent = current; init_context.thread_fn = thread_fn; init_context.data = data; init_completion(&init_context.init_done); thread = kthread_run(kvm_vm_worker_thread, &init_context, "%s-%d", name, task_pid_nr(current)); if (IS_ERR(thread)) return PTR_ERR(thread); /* kthread_run is never supposed to return NULL */ WARN_ON(thread == NULL); wait_for_completion(&init_context.init_done); if (!init_context.err) *thread_ptr = thread; return init_context.err; } |
| 1 1 2 2 7 8 7 8 8 8 8 8 158 118 35 66 83 9 36 35 3 33 33 9 9 89 3 158 158 9 66 33 8 8 83 8 66 33 83 8 85 84 8 8 7 85 85 6 6 83 83 140 77 88 88 2 4 2 3 1 2 2 2 2 2 2 2 8 119 8 85 83 3 85 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Copyright (C) Christoph Hellwig, 2002 */ #include <linux/capability.h> #include <linux/fs.h> #include <linux/xattr.h> #include <linux/posix_acl_xattr.h> #include <linux/slab.h> #include <linux/quotaops.h> #include <linux/security.h> #include "jfs_incore.h" #include "jfs_superblock.h" #include "jfs_dmap.h" #include "jfs_debug.h" #include "jfs_dinode.h" #include "jfs_extent.h" #include "jfs_metapage.h" #include "jfs_xattr.h" #include "jfs_acl.h" /* * jfs_xattr.c: extended attribute service * * Overall design -- * * Format: * * Extended attribute lists (jfs_ea_list) consist of an overall size (32 bit * value) and a variable (0 or more) number of extended attribute * entries. Each extended attribute entry (jfs_ea) is a <name,value> double * where <name> is constructed from a null-terminated ascii string * (1 ... 255 bytes in the name) and <value> is arbitrary 8 bit data * (1 ... 65535 bytes). The in-memory format is * * 0 1 2 4 4 + namelen + 1 * +-------+--------+--------+----------------+-------------------+ * | Flags | Name | Value | Name String \0 | Data . . . . | * | | Length | Length | | | * +-------+--------+--------+----------------+-------------------+ * * A jfs_ea_list then is structured as * * 0 4 4 + EA_SIZE(ea1) * +------------+-------------------+--------------------+----- * | Overall EA | First FEA Element | Second FEA Element | ..... * | List Size | | | * +------------+-------------------+--------------------+----- * * On-disk: * * FEALISTs are stored on disk using blocks allocated by dbAlloc() and * written directly. An EA list may be in-lined in the inode if there is * sufficient room available. */ struct ea_buffer { int flag; /* Indicates what storage xattr points to */ int max_size; /* largest xattr that fits in current buffer */ dxd_t new_ea; /* dxd to replace ea when modifying xattr */ struct metapage *mp; /* metapage containing ea list */ struct jfs_ea_list *xattr; /* buffer containing ea list */ }; /* * ea_buffer.flag values */ #define EA_INLINE 0x0001 #define EA_EXTENT 0x0002 #define EA_NEW 0x0004 #define EA_MALLOC 0x0008 /* * Mapping of on-disk attribute names: for on-disk attribute names with an * unknown prefix (not "system.", "user.", "security.", or "trusted."), the * prefix "os2." is prepended. On the way back to disk, "os2." prefixes are * stripped and we make sure that the remaining name does not start with one * of the know prefixes. */ static int is_known_namespace(const char *name) { if (strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) && strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) && strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) return false; return true; } static inline int name_size(struct jfs_ea *ea) { if (is_known_namespace(ea->name)) return ea->namelen; else return ea->namelen + XATTR_OS2_PREFIX_LEN; } static inline int copy_name(char *buffer, struct jfs_ea *ea) { int len = ea->namelen; if (!is_known_namespace(ea->name)) { memcpy(buffer, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN); buffer += XATTR_OS2_PREFIX_LEN; len += XATTR_OS2_PREFIX_LEN; } memcpy(buffer, ea->name, ea->namelen); buffer[ea->namelen] = 0; return len; } /* Forward references */ static void ea_release(struct inode *inode, struct ea_buffer *ea_buf); /* * NAME: ea_write_inline * * FUNCTION: Attempt to write an EA inline if area is available * * PRE CONDITIONS: * Already verified that the specified EA is small enough to fit inline * * PARAMETERS: * ip - Inode pointer * ealist - EA list pointer * size - size of ealist in bytes * ea - dxd_t structure to be filled in with necessary EA information * if we successfully copy the EA inline * * NOTES: * Checks if the inode's inline area is available. If so, copies EA inline * and sets <ea> fields appropriately. Otherwise, returns failure, EA will * have to be put into an extent. * * RETURNS: 0 for successful copy to inline area; -1 if area not available */ static int ea_write_inline(struct inode *ip, struct jfs_ea_list *ealist, int size, dxd_t * ea) { struct jfs_inode_info *ji = JFS_IP(ip); /* * Make sure we have an EA -- the NULL EA list is valid, but you * can't copy it! */ if (ealist && size > sizeof (struct jfs_ea_list)) { assert(size <= sizeof (ji->i_inline_ea)); /* * See if the space is available or if it is already being * used for an inline EA. */ if (!(ji->mode2 & INLINEEA) && !(ji->ea.flag & DXD_INLINE)) return -EPERM; DXDsize(ea, size); DXDlength(ea, 0); DXDaddress(ea, 0); memcpy(ji->i_inline_ea, ealist, size); ea->flag = DXD_INLINE; ji->mode2 &= ~INLINEEA; } else { ea->flag = 0; DXDsize(ea, 0); DXDlength(ea, 0); DXDaddress(ea, 0); /* Free up INLINE area */ if (ji->ea.flag & DXD_INLINE) ji->mode2 |= INLINEEA; } return 0; } /* * NAME: ea_write * * FUNCTION: Write an EA for an inode * * PRE CONDITIONS: EA has been verified * * PARAMETERS: * ip - Inode pointer * ealist - EA list pointer * size - size of ealist in bytes * ea - dxd_t structure to be filled in appropriately with where the * EA was copied * * NOTES: Will write EA inline if able to, otherwise allocates blocks for an * extent and synchronously writes it to those blocks. * * RETURNS: 0 for success; Anything else indicates failure */ static int ea_write(struct inode *ip, struct jfs_ea_list *ealist, int size, dxd_t * ea) { struct super_block *sb = ip->i_sb; struct jfs_inode_info *ji = JFS_IP(ip); struct jfs_sb_info *sbi = JFS_SBI(sb); int nblocks; s64 blkno; int rc = 0, i; char *cp; s32 nbytes, nb; s32 bytes_to_write; struct metapage *mp; /* * Quick check to see if this is an in-linable EA. Short EAs * and empty EAs are all in-linable, provided the space exists. */ if (!ealist || size <= sizeof (ji->i_inline_ea)) { if (!ea_write_inline(ip, ealist, size, ea)) return 0; } /* figure out how many blocks we need */ nblocks = (size + (sb->s_blocksize - 1)) >> sb->s_blocksize_bits; /* Allocate new blocks to quota. */ rc = dquot_alloc_block(ip, nblocks); if (rc) return rc; rc = dbAlloc(ip, INOHINT(ip), nblocks, &blkno); if (rc) { /*Rollback quota allocation. */ dquot_free_block(ip, nblocks); return rc; } /* * Now have nblocks worth of storage to stuff into the FEALIST. * loop over the FEALIST copying data into the buffer one page at * a time. */ cp = (char *) ealist; nbytes = size; for (i = 0; i < nblocks; i += sbi->nbperpage) { /* * Determine how many bytes for this request, and round up to * the nearest aggregate block size */ nb = min(PSIZE, nbytes); bytes_to_write = ((((nb + sb->s_blocksize - 1)) >> sb->s_blocksize_bits)) << sb->s_blocksize_bits; if (!(mp = get_metapage(ip, blkno + i, bytes_to_write, 1))) { rc = -EIO; goto failed; } memcpy(mp->data, cp, nb); /* * We really need a way to propagate errors for * forced writes like this one. --hch * * (__write_metapage => release_metapage => flush_metapage) */ #ifdef _JFS_FIXME if ((rc = flush_metapage(mp))) { /* * the write failed -- this means that the buffer * is still assigned and the blocks are not being * used. this seems like the best error recovery * we can get ... */ goto failed; } #else flush_metapage(mp); #endif cp += PSIZE; nbytes -= nb; } ea->flag = DXD_EXTENT; DXDsize(ea, le32_to_cpu(ealist->size)); DXDlength(ea, nblocks); DXDaddress(ea, blkno); /* Free up INLINE area */ if (ji->ea.flag & DXD_INLINE) ji->mode2 |= INLINEEA; return 0; failed: /* Rollback quota allocation. */ dquot_free_block(ip, nblocks); dbFree(ip, blkno, nblocks); return rc; } /* * NAME: ea_read_inline * * FUNCTION: Read an inlined EA into user's buffer * * PARAMETERS: * ip - Inode pointer * ealist - Pointer to buffer to fill in with EA * * RETURNS: 0 */ static int ea_read_inline(struct inode *ip, struct jfs_ea_list *ealist) { struct jfs_inode_info *ji = JFS_IP(ip); int ea_size = sizeDXD(&ji->ea); if (ea_size == 0) { ealist->size = 0; return 0; } /* Sanity Check */ if ((sizeDXD(&ji->ea) > sizeof (ji->i_inline_ea))) return -EIO; if (le32_to_cpu(((struct jfs_ea_list *) &ji->i_inline_ea)->size) != ea_size) return -EIO; memcpy(ealist, ji->i_inline_ea, ea_size); return 0; } /* * NAME: ea_read * * FUNCTION: copy EA data into user's buffer * * PARAMETERS: * ip - Inode pointer * ealist - Pointer to buffer to fill in with EA * * NOTES: If EA is inline calls ea_read_inline() to copy EA. * * RETURNS: 0 for success; other indicates failure */ static int ea_read(struct inode *ip, struct jfs_ea_list *ealist) { struct super_block *sb = ip->i_sb; struct jfs_inode_info *ji = JFS_IP(ip); struct jfs_sb_info *sbi = JFS_SBI(sb); int nblocks; s64 blkno; char *cp = (char *) ealist; int i; int nbytes, nb; s32 bytes_to_read; struct metapage *mp; /* quick check for in-line EA */ if (ji->ea.flag & DXD_INLINE) return ea_read_inline(ip, ealist); nbytes = sizeDXD(&ji->ea); if (!nbytes) { jfs_error(sb, "nbytes is 0\n"); return -EIO; } /* * Figure out how many blocks were allocated when this EA list was * originally written to disk. */ nblocks = lengthDXD(&ji->ea) << sbi->l2nbperpage; blkno = addressDXD(&ji->ea) << sbi->l2nbperpage; /* * I have found the disk blocks which were originally used to store * the FEALIST. now i loop over each contiguous block copying the * data into the buffer. */ for (i = 0; i < nblocks; i += sbi->nbperpage) { /* * Determine how many bytes for this request, and round up to * the nearest aggregate block size */ nb = min(PSIZE, nbytes); bytes_to_read = ((((nb + sb->s_blocksize - 1)) >> sb->s_blocksize_bits)) << sb->s_blocksize_bits; if (!(mp = read_metapage(ip, blkno + i, bytes_to_read, 1))) return -EIO; memcpy(cp, mp->data, nb); release_metapage(mp); cp += PSIZE; nbytes -= nb; } return 0; } /* * NAME: ea_get * * FUNCTION: Returns buffer containing existing extended attributes. * The size of the buffer will be the larger of the existing * attributes size, or min_size. * * The buffer, which may be inlined in the inode or in the * page cache must be release by calling ea_release or ea_put * * PARAMETERS: * inode - Inode pointer * ea_buf - Structure to be populated with ealist and its metadata * min_size- minimum size of buffer to be returned * * RETURNS: 0 for success; Other indicates failure */ static int ea_get(struct inode *inode, struct ea_buffer *ea_buf, int min_size) { struct jfs_inode_info *ji = JFS_IP(inode); struct super_block *sb = inode->i_sb; int size; int ea_size = sizeDXD(&ji->ea); int blocks_needed, current_blocks; s64 blkno; int rc; int quota_allocation = 0; /* When fsck.jfs clears a bad ea, it doesn't clear the size */ if (ji->ea.flag == 0) ea_size = 0; if (ea_size == 0) { if (min_size == 0) { ea_buf->flag = 0; ea_buf->max_size = 0; ea_buf->xattr = NULL; return 0; } if ((min_size <= sizeof (ji->i_inline_ea)) && (ji->mode2 & INLINEEA)) { ea_buf->flag = EA_INLINE | EA_NEW; ea_buf->max_size = sizeof (ji->i_inline_ea); ea_buf->xattr = (struct jfs_ea_list *) ji->i_inline_ea; DXDlength(&ea_buf->new_ea, 0); DXDaddress(&ea_buf->new_ea, 0); ea_buf->new_ea.flag = DXD_INLINE; DXDsize(&ea_buf->new_ea, min_size); return 0; } current_blocks = 0; } else if (ji->ea.flag & DXD_INLINE) { if (min_size <= sizeof (ji->i_inline_ea)) { ea_buf->flag = EA_INLINE; ea_buf->max_size = sizeof (ji->i_inline_ea); ea_buf->xattr = (struct jfs_ea_list *) ji->i_inline_ea; goto size_check; } current_blocks = 0; } else { if (!(ji->ea.flag & DXD_EXTENT)) { jfs_error(sb, "invalid ea.flag\n"); return -EIO; } current_blocks = (ea_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; } size = max(min_size, ea_size); if (size > PSIZE) { /* * To keep the rest of the code simple. Allocate a * contiguous buffer to work with. Make the buffer large * enough to make use of the whole extent. */ ea_buf->max_size = (size + sb->s_blocksize - 1) & ~(sb->s_blocksize - 1); ea_buf->xattr = kmalloc(ea_buf->max_size, GFP_KERNEL); if (ea_buf->xattr == NULL) return -ENOMEM; ea_buf->flag = EA_MALLOC; if (ea_size == 0) return 0; if ((rc = ea_read(inode, ea_buf->xattr))) { kfree(ea_buf->xattr); ea_buf->xattr = NULL; return rc; } goto size_check; } blocks_needed = (min_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; if (blocks_needed > current_blocks) { /* Allocate new blocks to quota. */ rc = dquot_alloc_block(inode, blocks_needed); if (rc) return -EDQUOT; quota_allocation = blocks_needed; rc = dbAlloc(inode, INOHINT(inode), (s64) blocks_needed, &blkno); if (rc) goto clean_up; DXDlength(&ea_buf->new_ea, blocks_needed); DXDaddress(&ea_buf->new_ea, blkno); ea_buf->new_ea.flag = DXD_EXTENT; DXDsize(&ea_buf->new_ea, min_size); ea_buf->flag = EA_EXTENT | EA_NEW; ea_buf->mp = get_metapage(inode, blkno, blocks_needed << sb->s_blocksize_bits, 1); if (ea_buf->mp == NULL) { dbFree(inode, blkno, (s64) blocks_needed); rc = -EIO; goto clean_up; } ea_buf->xattr = ea_buf->mp->data; ea_buf->max_size = (min_size + sb->s_blocksize - 1) & ~(sb->s_blocksize - 1); if (ea_size == 0) return 0; if ((rc = ea_read(inode, ea_buf->xattr))) { discard_metapage(ea_buf->mp); dbFree(inode, blkno, (s64) blocks_needed); goto clean_up; } goto size_check; } ea_buf->flag = EA_EXTENT; ea_buf->mp = read_metapage(inode, addressDXD(&ji->ea), lengthDXD(&ji->ea) << sb->s_blocksize_bits, 1); if (ea_buf->mp == NULL) { rc = -EIO; goto clean_up; } ea_buf->xattr = ea_buf->mp->data; ea_buf->max_size = (ea_size + sb->s_blocksize - 1) & ~(sb->s_blocksize - 1); size_check: if (EALIST_SIZE(ea_buf->xattr) != ea_size) { int size = min_t(int, EALIST_SIZE(ea_buf->xattr), ea_size); printk(KERN_ERR "ea_get: invalid extended attribute\n"); print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, ea_buf->xattr, size, 1); ea_release(inode, ea_buf); rc = -EIO; goto clean_up; } return ea_size; clean_up: /* Rollback quota allocation */ if (quota_allocation) dquot_free_block(inode, quota_allocation); return (rc); } static void ea_release(struct inode *inode, struct ea_buffer *ea_buf) { if (ea_buf->flag & EA_MALLOC) kfree(ea_buf->xattr); else if (ea_buf->flag & EA_EXTENT) { assert(ea_buf->mp); release_metapage(ea_buf->mp); if (ea_buf->flag & EA_NEW) dbFree(inode, addressDXD(&ea_buf->new_ea), lengthDXD(&ea_buf->new_ea)); } } static int ea_put(tid_t tid, struct inode *inode, struct ea_buffer *ea_buf, int new_size) { struct jfs_inode_info *ji = JFS_IP(inode); unsigned long old_blocks, new_blocks; int rc = 0; if (new_size == 0) { ea_release(inode, ea_buf); ea_buf = NULL; } else if (ea_buf->flag & EA_INLINE) { assert(new_size <= sizeof (ji->i_inline_ea)); ji->mode2 &= ~INLINEEA; ea_buf->new_ea.flag = DXD_INLINE; DXDsize(&ea_buf->new_ea, new_size); DXDaddress(&ea_buf->new_ea, 0); DXDlength(&ea_buf->new_ea, 0); } else if (ea_buf->flag & EA_MALLOC) { rc = ea_write(inode, ea_buf->xattr, new_size, &ea_buf->new_ea); kfree(ea_buf->xattr); } else if (ea_buf->flag & EA_NEW) { /* We have already allocated a new dxd */ flush_metapage(ea_buf->mp); } else { /* ->xattr must point to original ea's metapage */ rc = ea_write(inode, ea_buf->xattr, new_size, &ea_buf->new_ea); discard_metapage(ea_buf->mp); } if (rc) return rc; old_blocks = new_blocks = 0; if (ji->ea.flag & DXD_EXTENT) { invalidate_dxd_metapages(inode, ji->ea); old_blocks = lengthDXD(&ji->ea); } if (ea_buf) { txEA(tid, inode, &ji->ea, &ea_buf->new_ea); if (ea_buf->new_ea.flag & DXD_EXTENT) { new_blocks = lengthDXD(&ea_buf->new_ea); if (ji->ea.flag & DXD_INLINE) ji->mode2 |= INLINEEA; } ji->ea = ea_buf->new_ea; } else { txEA(tid, inode, &ji->ea, NULL); if (ji->ea.flag & DXD_INLINE) ji->mode2 |= INLINEEA; ji->ea.flag = 0; ji->ea.size = 0; } /* If old blocks exist, they must be removed from quota allocation. */ if (old_blocks) dquot_free_block(inode, old_blocks); inode_set_ctime_current(inode); return 0; } int __jfs_setxattr(tid_t tid, struct inode *inode, const char *name, const void *value, size_t value_len, int flags) { struct jfs_ea_list *ealist; struct jfs_ea *ea, *old_ea = NULL, *next_ea = NULL; struct ea_buffer ea_buf; int old_ea_size = 0; int xattr_size; int new_size; int namelen = strlen(name); int found = 0; int rc; int length; down_write(&JFS_IP(inode)->xattr_sem); xattr_size = ea_get(inode, &ea_buf, 0); if (xattr_size < 0) { rc = xattr_size; goto out; } again: ealist = (struct jfs_ea_list *) ea_buf.xattr; new_size = sizeof (struct jfs_ea_list); if (xattr_size) { for (ea = FIRST_EA(ealist); ea < END_EALIST(ealist); ea = NEXT_EA(ea)) { if ((namelen == ea->namelen) && (memcmp(name, ea->name, namelen) == 0)) { found = 1; if (flags & XATTR_CREATE) { rc = -EEXIST; goto release; } old_ea = ea; old_ea_size = EA_SIZE(ea); next_ea = NEXT_EA(ea); } else new_size += EA_SIZE(ea); } } if (!found) { if (flags & XATTR_REPLACE) { rc = -ENODATA; goto release; } if (value == NULL) { rc = 0; goto release; } } if (value) new_size += sizeof (struct jfs_ea) + namelen + 1 + value_len; if (new_size > ea_buf.max_size) { /* * We need to allocate more space for merged ea list. * We should only have loop to again: once. */ ea_release(inode, &ea_buf); xattr_size = ea_get(inode, &ea_buf, new_size); if (xattr_size < 0) { rc = xattr_size; goto out; } goto again; } /* Remove old ea of the same name */ if (found) { /* number of bytes following target EA */ length = (char *) END_EALIST(ealist) - (char *) next_ea; if (length > 0) memmove(old_ea, next_ea, length); xattr_size -= old_ea_size; } /* Add new entry to the end */ if (value) { if (xattr_size == 0) /* Completely new ea list */ xattr_size = sizeof (struct jfs_ea_list); /* * The size of EA value is limitted by on-disk format up to * __le16, there would be an overflow if the size is equal * to XATTR_SIZE_MAX (65536). In order to avoid this issue, * we can pre-checkup the value size against USHRT_MAX, and * return -E2BIG in this case, which is consistent with the * VFS setxattr interface. */ if (value_len >= USHRT_MAX) { rc = -E2BIG; goto release; } ea = (struct jfs_ea *) ((char *) ealist + xattr_size); ea->flag = 0; ea->namelen = namelen; ea->valuelen = (cpu_to_le16(value_len)); memcpy(ea->name, name, namelen); ea->name[namelen] = 0; if (value_len) memcpy(&ea->name[namelen + 1], value, value_len); xattr_size += EA_SIZE(ea); } /* DEBUG - If we did this right, these number match */ if (xattr_size != new_size) { printk(KERN_ERR "__jfs_setxattr: xattr_size = %d, new_size = %d\n", xattr_size, new_size); rc = -EINVAL; goto release; } /* * If we're left with an empty list, there's no ea */ if (new_size == sizeof (struct jfs_ea_list)) new_size = 0; ealist->size = cpu_to_le32(new_size); rc = ea_put(tid, inode, &ea_buf, new_size); goto out; release: ea_release(inode, &ea_buf); out: up_write(&JFS_IP(inode)->xattr_sem); return rc; } ssize_t __jfs_getxattr(struct inode *inode, const char *name, void *data, size_t buf_size) { struct jfs_ea_list *ealist; struct jfs_ea *ea, *ealist_end; struct ea_buffer ea_buf; int xattr_size; ssize_t size; int namelen = strlen(name); char *value; down_read(&JFS_IP(inode)->xattr_sem); xattr_size = ea_get(inode, &ea_buf, 0); if (xattr_size < 0) { size = xattr_size; goto out; } if (xattr_size == 0) goto not_found; ealist = (struct jfs_ea_list *) ea_buf.xattr; ealist_end = END_EALIST(ealist); /* Find the named attribute */ for (ea = FIRST_EA(ealist); ea < ealist_end; ea = NEXT_EA(ea)) { if (unlikely(ea + 1 > ealist_end) || unlikely(NEXT_EA(ea) > ealist_end)) { size = -EUCLEAN; goto release; } if ((namelen == ea->namelen) && memcmp(name, ea->name, namelen) == 0) { /* Found it */ size = le16_to_cpu(ea->valuelen); if (!data) goto release; else if (size > buf_size) { size = -ERANGE; goto release; } value = ((char *) &ea->name) + ea->namelen + 1; memcpy(data, value, size); goto release; } } not_found: size = -ENODATA; release: ea_release(inode, &ea_buf); out: up_read(&JFS_IP(inode)->xattr_sem); return size; } /* * No special permissions are needed to list attributes except for trusted.* */ static inline int can_list(struct jfs_ea *ea) { return (strncmp(ea->name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) || capable(CAP_SYS_ADMIN)); } ssize_t jfs_listxattr(struct dentry * dentry, char *data, size_t buf_size) { struct inode *inode = d_inode(dentry); char *buffer; ssize_t size = 0; int xattr_size; struct jfs_ea_list *ealist; struct jfs_ea *ea, *ealist_end; struct ea_buffer ea_buf; down_read(&JFS_IP(inode)->xattr_sem); xattr_size = ea_get(inode, &ea_buf, 0); if (xattr_size < 0) { size = xattr_size; goto out; } if (xattr_size == 0) goto release; ealist = (struct jfs_ea_list *) ea_buf.xattr; ealist_end = END_EALIST(ealist); /* compute required size of list */ for (ea = FIRST_EA(ealist); ea < ealist_end; ea = NEXT_EA(ea)) { if (unlikely(ea + 1 > ealist_end) || unlikely(NEXT_EA(ea) > ealist_end)) { size = -EUCLEAN; goto release; } if (can_list(ea)) size += name_size(ea) + 1; } if (!data) goto release; if (size > buf_size) { size = -ERANGE; goto release; } /* Copy attribute names to buffer */ buffer = data; for (ea = FIRST_EA(ealist); ea < END_EALIST(ealist); ea = NEXT_EA(ea)) { if (can_list(ea)) { int namelen = copy_name(buffer, ea); buffer += namelen + 1; } } release: ea_release(inode, &ea_buf); out: up_read(&JFS_IP(inode)->xattr_sem); return size; } static int __jfs_xattr_set(struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct jfs_inode_info *ji = JFS_IP(inode); tid_t tid; int rc; tid = txBegin(inode->i_sb, 0); mutex_lock(&ji->commit_mutex); rc = __jfs_setxattr(tid, inode, name, value, size, flags); if (!rc) rc = txCommit(tid, 1, &inode, 0); txEnd(tid); mutex_unlock(&ji->commit_mutex); return rc; } static int jfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *value, size_t size) { name = xattr_full_name(handler, name); return __jfs_getxattr(inode, name, value, size); } static int jfs_xattr_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) { name = xattr_full_name(handler, name); return __jfs_xattr_set(inode, name, value, size, flags); } static int jfs_xattr_get_os2(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *value, size_t size) { if (is_known_namespace(name)) return -EOPNOTSUPP; return __jfs_getxattr(inode, name, value, size); } static int jfs_xattr_set_os2(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) { if (is_known_namespace(name)) return -EOPNOTSUPP; return __jfs_xattr_set(inode, name, value, size, flags); } static const struct xattr_handler jfs_user_xattr_handler = { .prefix = XATTR_USER_PREFIX, .get = jfs_xattr_get, .set = jfs_xattr_set, }; static const struct xattr_handler jfs_os2_xattr_handler = { .prefix = XATTR_OS2_PREFIX, .get = jfs_xattr_get_os2, .set = jfs_xattr_set_os2, }; static const struct xattr_handler jfs_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, .get = jfs_xattr_get, .set = jfs_xattr_set, }; static const struct xattr_handler jfs_trusted_xattr_handler = { .prefix = XATTR_TRUSTED_PREFIX, .get = jfs_xattr_get, .set = jfs_xattr_set, }; const struct xattr_handler * const jfs_xattr_handlers[] = { &jfs_os2_xattr_handler, &jfs_user_xattr_handler, &jfs_security_xattr_handler, &jfs_trusted_xattr_handler, NULL, }; #ifdef CONFIG_JFS_SECURITY static int jfs_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { const struct xattr *xattr; tid_t *tid = fs_info; char *name; int err = 0; for (xattr = xattr_array; xattr->name != NULL; xattr++) { name = kmalloc(XATTR_SECURITY_PREFIX_LEN + strlen(xattr->name) + 1, GFP_NOFS); if (!name) { err = -ENOMEM; break; } strcpy(name, XATTR_SECURITY_PREFIX); strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name); err = __jfs_setxattr(*tid, inode, name, xattr->value, xattr->value_len, 0); kfree(name); if (err < 0) break; } return err; } int jfs_init_security(tid_t tid, struct inode *inode, struct inode *dir, const struct qstr *qstr) { return security_inode_init_security(inode, dir, qstr, &jfs_initxattrs, &tid); } #endif |
| 7 2 190 190 475 5 474 87 229 13 225 190 89 189 189 195 190 292 173 223 218 218 218 56 56 2 120 216 213 160 160 160 175 175 175 18 18 18 122 123 122 122 122 122 122 78 23 69 66 3 3 3 27 13 27 13 75 75 86 77 1 1 1 1 1 1 1 2 1 37 30 30 9 9 7 2 9 9 78 7 71 17 17 17 6 38 38 37 30 35 13 12 12 87 87 158 11 95 70 69 70 88 85 76 87 53 28 6 60 60 56 60 56 56 53 56 56 46 46 39 19 16 9 9 232 232 231 232 232 232 232 232 232 232 232 232 232 232 231 232 232 231 232 232 232 232 85 232 232 232 232 72 67 67 63 63 63 46 9 95 87 1 88 4 4 4 4 4 4 4 5 5 5 3 1 4 4 4 4 125 125 125 125 125 88 88 88 2 85 84 76 9 2 3 3 3 3 3 90 90 89 90 90 173 174 85 174 15 159 173 172 86 172 172 172 170 159 160 159 159 159 158 11 11 11 175 103 87 15 160 173 174 3 172 172 172 3 347 347 98 127 196 196 37 37 13 5 5 5 5 5 5 4 5 12 12 2 12 12 15 15 3 3 15 13 13 13 12 12 70 4 67 94 93 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2007 Oracle. All rights reserved. */ #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/radix-tree.h> #include <linux/writeback.h> #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/slab.h> #include <linux/migrate.h> #include <linux/ratelimit.h> #include <linux/uuid.h> #include <linux/semaphore.h> #include <linux/error-injection.h> #include <linux/crc32c.h> #include <linux/sched/mm.h> #include <asm/unaligned.h> #include <crypto/hash.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" #include "btrfs_inode.h" #include "bio.h" #include "print-tree.h" #include "locking.h" #include "tree-log.h" #include "free-space-cache.h" #include "free-space-tree.h" #include "dev-replace.h" #include "raid56.h" #include "sysfs.h" #include "qgroup.h" #include "compression.h" #include "tree-checker.h" #include "ref-verify.h" #include "block-group.h" #include "discard.h" #include "space-info.h" #include "zoned.h" #include "subpage.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #include "root-tree.h" #include "defrag.h" #include "uuid-tree.h" #include "relocation.h" #include "scrub.h" #include "super.h" #define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\ BTRFS_HEADER_FLAG_RELOC |\ BTRFS_SUPER_FLAG_ERROR |\ BTRFS_SUPER_FLAG_SEEDING |\ BTRFS_SUPER_FLAG_METADUMP |\ BTRFS_SUPER_FLAG_METADUMP_V2) static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info); static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info); static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info) { if (fs_info->csum_shash) crypto_free_shash(fs_info->csum_shash); } /* * Compute the csum of a btree block and store the result to provided buffer. */ static void csum_tree_block(struct extent_buffer *buf, u8 *result) { struct btrfs_fs_info *fs_info = buf->fs_info; int num_pages; u32 first_page_part; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); char *kaddr; int i; shash->tfm = fs_info->csum_shash; crypto_shash_init(shash); if (buf->addr) { /* Pages are contiguous, handle them as a big one. */ kaddr = buf->addr; first_page_part = fs_info->nodesize; num_pages = 1; } else { kaddr = folio_address(buf->folios[0]); first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize); num_pages = num_extent_pages(buf); } crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, first_page_part - BTRFS_CSUM_SIZE); /* * Multiple single-page folios case would reach here. * * nodesize <= PAGE_SIZE and large folio all handled by above * crypto_shash_update() already. */ for (i = 1; i < num_pages && INLINE_EXTENT_BUFFER_PAGES > 1; i++) { kaddr = folio_address(buf->folios[i]); crypto_shash_update(shash, kaddr, PAGE_SIZE); } memset(result, 0, BTRFS_CSUM_SIZE); crypto_shash_final(shash, result); } /* * we can't consider a given block up to date unless the transid of the * block matches the transid in the parent node's pointer. This is how we * detect blocks that either didn't get written at all or got written * in the wrong place. */ int btrfs_buffer_uptodate(struct extent_buffer *eb, u64 parent_transid, int atomic) { if (!extent_buffer_uptodate(eb)) return 0; if (!parent_transid || btrfs_header_generation(eb) == parent_transid) return 1; if (atomic) return -EAGAIN; if (!extent_buffer_uptodate(eb) || btrfs_header_generation(eb) != parent_transid) { btrfs_err_rl(eb->fs_info, "parent transid verify failed on logical %llu mirror %u wanted %llu found %llu", eb->start, eb->read_mirror, parent_transid, btrfs_header_generation(eb)); clear_extent_buffer_uptodate(eb); return 0; } return 1; } static bool btrfs_supported_super_csum(u16 csum_type) { switch (csum_type) { case BTRFS_CSUM_TYPE_CRC32: case BTRFS_CSUM_TYPE_XXHASH: case BTRFS_CSUM_TYPE_SHA256: case BTRFS_CSUM_TYPE_BLAKE2: return true; default: return false; } } /* * Return 0 if the superblock checksum type matches the checksum value of that * algorithm. Pass the raw disk superblock data. */ int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, const struct btrfs_super_block *disk_sb) { char result[BTRFS_CSUM_SIZE]; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); shash->tfm = fs_info->csum_shash; /* * The super_block structure does not span the whole * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space is * filled with zeros and is included in the checksum. */ crypto_shash_digest(shash, (const u8 *)disk_sb + BTRFS_CSUM_SIZE, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, result); if (memcmp(disk_sb->csum, result, fs_info->csum_size)) return 1; return 0; } static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num) { struct btrfs_fs_info *fs_info = eb->fs_info; int num_folios = num_extent_folios(eb); int ret = 0; if (sb_rdonly(fs_info->sb)) return -EROFS; for (int i = 0; i < num_folios; i++) { struct folio *folio = eb->folios[i]; u64 start = max_t(u64, eb->start, folio_pos(folio)); u64 end = min_t(u64, eb->start + eb->len, folio_pos(folio) + eb->folio_size); u32 len = end - start; ret = btrfs_repair_io_failure(fs_info, 0, start, len, start, folio, offset_in_folio(folio, start), mirror_num); if (ret) break; } return ret; } /* * helper to read a given tree block, doing retries as required when * the checksums don't match and we have alternate mirrors to try. * * @check: expected tree parentness check, see the comments of the * structure for details. */ int btrfs_read_extent_buffer(struct extent_buffer *eb, const struct btrfs_tree_parent_check *check) { struct btrfs_fs_info *fs_info = eb->fs_info; int failed = 0; int ret; int num_copies = 0; int mirror_num = 0; int failed_mirror = 0; ASSERT(check); while (1) { clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num, check); if (!ret) break; num_copies = btrfs_num_copies(fs_info, eb->start, eb->len); if (num_copies == 1) break; if (!failed_mirror) { failed = 1; failed_mirror = eb->read_mirror; } mirror_num++; if (mirror_num == failed_mirror) mirror_num++; if (mirror_num > num_copies) break; } if (failed && !ret && failed_mirror) btrfs_repair_eb_io_failure(eb, failed_mirror); return ret; } /* * Checksum a dirty tree block before IO. */ blk_status_t btree_csum_one_bio(struct btrfs_bio *bbio) { struct extent_buffer *eb = bbio->private; struct btrfs_fs_info *fs_info = eb->fs_info; u64 found_start = btrfs_header_bytenr(eb); u64 last_trans; u8 result[BTRFS_CSUM_SIZE]; int ret; /* Btree blocks are always contiguous on disk. */ if (WARN_ON_ONCE(bbio->file_offset != eb->start)) return BLK_STS_IOERR; if (WARN_ON_ONCE(bbio->bio.bi_iter.bi_size != eb->len)) return BLK_STS_IOERR; /* * If an extent_buffer is marked as EXTENT_BUFFER_ZONED_ZEROOUT, don't * checksum it but zero-out its content. This is done to preserve * ordering of I/O without unnecessarily writing out data. */ if (test_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags)) { memzero_extent_buffer(eb, 0, eb->len); return BLK_STS_OK; } if (WARN_ON_ONCE(found_start != eb->start)) return BLK_STS_IOERR; if (WARN_ON(!btrfs_folio_test_uptodate(fs_info, eb->folios[0], eb->start, eb->len))) return BLK_STS_IOERR; ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid, offsetof(struct btrfs_header, fsid), BTRFS_FSID_SIZE) == 0); csum_tree_block(eb, result); if (btrfs_header_level(eb)) ret = btrfs_check_node(eb); else ret = btrfs_check_leaf(eb); if (ret < 0) goto error; /* * Also check the generation, the eb reached here must be newer than * last committed. Or something seriously wrong happened. */ last_trans = btrfs_get_last_trans_committed(fs_info); if (unlikely(btrfs_header_generation(eb) <= last_trans)) { ret = -EUCLEAN; btrfs_err(fs_info, "block=%llu bad generation, have %llu expect > %llu", eb->start, btrfs_header_generation(eb), last_trans); goto error; } write_extent_buffer(eb, result, 0, fs_info->csum_size); return BLK_STS_OK; error: btrfs_print_tree(eb, 0); btrfs_err(fs_info, "block=%llu write time tree block corruption detected", eb->start); /* * Be noisy if this is an extent buffer from a log tree. We don't abort * a transaction in case there's a bad log tree extent buffer, we just * fallback to a transaction commit. Still we want to know when there is * a bad log tree extent buffer, as that may signal a bug somewhere. */ WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) || btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID); return errno_to_blk_status(ret); } static bool check_tree_block_fsid(struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs; u8 fsid[BTRFS_FSID_SIZE]; read_extent_buffer(eb, fsid, offsetof(struct btrfs_header, fsid), BTRFS_FSID_SIZE); /* * alloc_fsid_devices() copies the fsid into fs_devices::metadata_uuid. * This is then overwritten by metadata_uuid if it is present in the * device_list_add(). The same true for a seed device as well. So use of * fs_devices::metadata_uuid is appropriate here. */ if (memcmp(fsid, fs_info->fs_devices->metadata_uuid, BTRFS_FSID_SIZE) == 0) return false; list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) if (!memcmp(fsid, seed_devs->fsid, BTRFS_FSID_SIZE)) return false; return true; } /* Do basic extent buffer checks at read time */ int btrfs_validate_extent_buffer(struct extent_buffer *eb, const struct btrfs_tree_parent_check *check) { struct btrfs_fs_info *fs_info = eb->fs_info; u64 found_start; const u32 csum_size = fs_info->csum_size; u8 found_level; u8 result[BTRFS_CSUM_SIZE]; const u8 *header_csum; int ret = 0; const bool ignore_csum = btrfs_test_opt(fs_info, IGNOREMETACSUMS); ASSERT(check); found_start = btrfs_header_bytenr(eb); if (found_start != eb->start) { btrfs_err_rl(fs_info, "bad tree block start, mirror %u want %llu have %llu", eb->read_mirror, eb->start, found_start); ret = -EIO; goto out; } if (check_tree_block_fsid(eb)) { btrfs_err_rl(fs_info, "bad fsid on logical %llu mirror %u", eb->start, eb->read_mirror); ret = -EIO; goto out; } found_level = btrfs_header_level(eb); if (found_level >= BTRFS_MAX_LEVEL) { btrfs_err(fs_info, "bad tree block level, mirror %u level %d on logical %llu", eb->read_mirror, btrfs_header_level(eb), eb->start); ret = -EIO; goto out; } csum_tree_block(eb, result); header_csum = folio_address(eb->folios[0]) + get_eb_offset_in_folio(eb, offsetof(struct btrfs_header, csum)); if (memcmp(result, header_csum, csum_size) != 0) { btrfs_warn_rl(fs_info, "checksum verify failed on logical %llu mirror %u wanted " CSUM_FMT " found " CSUM_FMT " level %d%s", eb->start, eb->read_mirror, CSUM_FMT_VALUE(csum_size, header_csum), CSUM_FMT_VALUE(csum_size, result), btrfs_header_level(eb), ignore_csum ? ", ignored" : ""); if (!ignore_csum) { ret = -EUCLEAN; goto out; } } if (found_level != check->level) { btrfs_err(fs_info, "level verify failed on logical %llu mirror %u wanted %u found %u", eb->start, eb->read_mirror, check->level, found_level); ret = -EIO; goto out; } if (unlikely(check->transid && btrfs_header_generation(eb) != check->transid)) { btrfs_err_rl(eb->fs_info, "parent transid verify failed on logical %llu mirror %u wanted %llu found %llu", eb->start, eb->read_mirror, check->transid, btrfs_header_generation(eb)); ret = -EIO; goto out; } if (check->has_first_key) { const struct btrfs_key *expect_key = &check->first_key; struct btrfs_key found_key; if (found_level) btrfs_node_key_to_cpu(eb, &found_key, 0); else btrfs_item_key_to_cpu(eb, &found_key, 0); if (unlikely(btrfs_comp_cpu_keys(expect_key, &found_key))) { btrfs_err(fs_info, "tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)", eb->start, check->transid, expect_key->objectid, expect_key->type, expect_key->offset, found_key.objectid, found_key.type, found_key.offset); ret = -EUCLEAN; goto out; } } if (check->owner_root) { ret = btrfs_check_eb_owner(eb, check->owner_root); if (ret < 0) goto out; } /* * If this is a leaf block and it is corrupt, set the corrupt bit so * that we don't try and read the other copies of this block, just * return -EIO. */ if (found_level == 0 && btrfs_check_leaf(eb)) { set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); ret = -EIO; } if (found_level > 0 && btrfs_check_node(eb)) ret = -EIO; if (ret) btrfs_err(fs_info, "read time tree block corruption detected on logical %llu mirror %u", eb->start, eb->read_mirror); out: return ret; } #ifdef CONFIG_MIGRATION static int btree_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { /* * we can't safely write a btree page from here, * we haven't done the locking hook */ if (folio_test_dirty(src)) return -EAGAIN; /* * Buffers may be managed in a filesystem specific way. * We must have no buffers or drop them. */ if (folio_get_private(src) && !filemap_release_folio(src, GFP_KERNEL)) return -EAGAIN; return migrate_folio(mapping, dst, src, mode); } #else #define btree_migrate_folio NULL #endif static int btree_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; if (wbc->sync_mode == WB_SYNC_NONE) { struct btrfs_fs_info *fs_info; if (wbc->for_kupdate) return 0; fs_info = inode_to_fs_info(mapping->host); /* this is a bit racy, but that's ok */ ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes, BTRFS_DIRTY_METADATA_THRESH, fs_info->dirty_metadata_batch); if (ret < 0) return 0; } return btree_write_cache_pages(mapping, wbc); } static bool btree_release_folio(struct folio *folio, gfp_t gfp_flags) { if (folio_test_writeback(folio) || folio_test_dirty(folio)) return false; return try_release_extent_buffer(&folio->page); } static void btree_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct extent_io_tree *tree; tree = &folio_to_inode(folio)->io_tree; extent_invalidate_folio(tree, folio, offset); btree_release_folio(folio, GFP_NOFS); if (folio_get_private(folio)) { btrfs_warn(folio_to_fs_info(folio), "folio private not zero on folio %llu", (unsigned long long)folio_pos(folio)); folio_detach_private(folio); } } #ifdef DEBUG static bool btree_dirty_folio(struct address_space *mapping, struct folio *folio) { struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); struct btrfs_subpage_info *spi = fs_info->subpage_info; struct btrfs_subpage *subpage; struct extent_buffer *eb; int cur_bit = 0; u64 page_start = folio_pos(folio); if (fs_info->sectorsize == PAGE_SIZE) { eb = folio_get_private(folio); BUG_ON(!eb); BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); BUG_ON(!atomic_read(&eb->refs)); btrfs_assert_tree_write_locked(eb); return filemap_dirty_folio(mapping, folio); } ASSERT(spi); subpage = folio_get_private(folio); for (cur_bit = spi->dirty_offset; cur_bit < spi->dirty_offset + spi->bitmap_nr_bits; cur_bit++) { unsigned long flags; u64 cur; spin_lock_irqsave(&subpage->lock, flags); if (!test_bit(cur_bit, subpage->bitmaps)) { spin_unlock_irqrestore(&subpage->lock, flags); continue; } spin_unlock_irqrestore(&subpage->lock, flags); cur = page_start + cur_bit * fs_info->sectorsize; eb = find_extent_buffer(fs_info, cur); ASSERT(eb); ASSERT(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); ASSERT(atomic_read(&eb->refs)); btrfs_assert_tree_write_locked(eb); free_extent_buffer(eb); cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits) - 1; } return filemap_dirty_folio(mapping, folio); } #else #define btree_dirty_folio filemap_dirty_folio #endif static const struct address_space_operations btree_aops = { .writepages = btree_writepages, .release_folio = btree_release_folio, .invalidate_folio = btree_invalidate_folio, .migrate_folio = btree_migrate_folio, .dirty_folio = btree_dirty_folio, }; struct extent_buffer *btrfs_find_create_tree_block( struct btrfs_fs_info *fs_info, u64 bytenr, u64 owner_root, int level) { if (btrfs_is_testing(fs_info)) return alloc_test_extent_buffer(fs_info, bytenr); return alloc_extent_buffer(fs_info, bytenr, owner_root, level); } /* * Read tree block at logical address @bytenr and do variant basic but critical * verification. * * @check: expected tree parentness check, see comments of the * structure for details. */ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, struct btrfs_tree_parent_check *check) { struct extent_buffer *buf = NULL; int ret; ASSERT(check); buf = btrfs_find_create_tree_block(fs_info, bytenr, check->owner_root, check->level); if (IS_ERR(buf)) return buf; ret = btrfs_read_extent_buffer(buf, check); if (ret) { free_extent_buffer_stale(buf); return ERR_PTR(ret); } return buf; } static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, u64 objectid) { bool dummy = btrfs_is_testing(fs_info); memset(&root->root_key, 0, sizeof(root->root_key)); memset(&root->root_item, 0, sizeof(root->root_item)); memset(&root->defrag_progress, 0, sizeof(root->defrag_progress)); root->fs_info = fs_info; root->root_key.objectid = objectid; root->node = NULL; root->commit_root = NULL; root->state = 0; RB_CLEAR_NODE(&root->rb_node); btrfs_set_root_last_trans(root, 0); root->free_objectid = 0; root->nr_delalloc_inodes = 0; root->nr_ordered_extents = 0; xa_init(&root->inodes); xa_init(&root->delayed_nodes); btrfs_init_root_block_rsv(root); INIT_LIST_HEAD(&root->dirty_list); INIT_LIST_HEAD(&root->root_list); INIT_LIST_HEAD(&root->delalloc_inodes); INIT_LIST_HEAD(&root->delalloc_root); INIT_LIST_HEAD(&root->ordered_extents); INIT_LIST_HEAD(&root->ordered_root); INIT_LIST_HEAD(&root->reloc_dirty_list); spin_lock_init(&root->delalloc_lock); spin_lock_init(&root->ordered_extent_lock); spin_lock_init(&root->accounting_lock); spin_lock_init(&root->qgroup_meta_rsv_lock); mutex_init(&root->objectid_mutex); mutex_init(&root->log_mutex); mutex_init(&root->ordered_extent_mutex); mutex_init(&root->delalloc_mutex); init_waitqueue_head(&root->qgroup_flush_wait); init_waitqueue_head(&root->log_writer_wait); init_waitqueue_head(&root->log_commit_wait[0]); init_waitqueue_head(&root->log_commit_wait[1]); INIT_LIST_HEAD(&root->log_ctxs[0]); INIT_LIST_HEAD(&root->log_ctxs[1]); atomic_set(&root->log_commit[0], 0); atomic_set(&root->log_commit[1], 0); atomic_set(&root->log_writers, 0); atomic_set(&root->log_batch, 0); refcount_set(&root->refs, 1); atomic_set(&root->snapshot_force_cow, 0); atomic_set(&root->nr_swapfiles, 0); btrfs_set_root_log_transid(root, 0); root->log_transid_committed = -1; btrfs_set_root_last_log_commit(root, 0); root->anon_dev = 0; if (!dummy) { extent_io_tree_init(fs_info, &root->dirty_log_pages, IO_TREE_ROOT_DIRTY_LOG_PAGES); extent_io_tree_init(fs_info, &root->log_csum_range, IO_TREE_LOG_CSUM_RANGE); } spin_lock_init(&root->root_item_lock); btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks); #ifdef CONFIG_BTRFS_DEBUG INIT_LIST_HEAD(&root->leak_list); spin_lock(&fs_info->fs_roots_radix_lock); list_add_tail(&root->leak_list, &fs_info->allocated_roots); spin_unlock(&fs_info->fs_roots_radix_lock); #endif } static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info, u64 objectid, gfp_t flags) { struct btrfs_root *root = kzalloc(sizeof(*root), flags); if (root) __setup_root(root, fs_info, objectid); return root; } #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS /* Should only be used by the testing infrastructure */ struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; if (!fs_info) return ERR_PTR(-EINVAL); root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID, GFP_KERNEL); if (!root) return ERR_PTR(-ENOMEM); /* We don't use the stripesize in selftest, set it as sectorsize */ root->alloc_bytenr = 0; return root; } #endif static int global_root_cmp(struct rb_node *a_node, const struct rb_node *b_node) { const struct btrfs_root *a = rb_entry(a_node, struct btrfs_root, rb_node); const struct btrfs_root *b = rb_entry(b_node, struct btrfs_root, rb_node); return btrfs_comp_cpu_keys(&a->root_key, &b->root_key); } static int global_root_key_cmp(const void *k, const struct rb_node *node) { const struct btrfs_key *key = k; const struct btrfs_root *root = rb_entry(node, struct btrfs_root, rb_node); return btrfs_comp_cpu_keys(key, &root->root_key); } int btrfs_global_root_insert(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; struct rb_node *tmp; int ret = 0; write_lock(&fs_info->global_root_lock); tmp = rb_find_add(&root->rb_node, &fs_info->global_root_tree, global_root_cmp); write_unlock(&fs_info->global_root_lock); if (tmp) { ret = -EEXIST; btrfs_warn(fs_info, "global root %llu %llu already exists", btrfs_root_id(root), root->root_key.offset); } return ret; } void btrfs_global_root_delete(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; write_lock(&fs_info->global_root_lock); rb_erase(&root->rb_node, &fs_info->global_root_tree); write_unlock(&fs_info->global_root_lock); } struct btrfs_root *btrfs_global_root(struct btrfs_fs_info *fs_info, struct btrfs_key *key) { struct rb_node *node; struct btrfs_root *root = NULL; read_lock(&fs_info->global_root_lock); node = rb_find(key, &fs_info->global_root_tree, global_root_key_cmp); if (node) root = container_of(node, struct btrfs_root, rb_node); read_unlock(&fs_info->global_root_lock); return root; } static u64 btrfs_global_root_id(struct btrfs_fs_info *fs_info, u64 bytenr) { struct btrfs_block_group *block_group; u64 ret; if (!btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) return 0; if (bytenr) block_group = btrfs_lookup_block_group(fs_info, bytenr); else block_group = btrfs_lookup_first_block_group(fs_info, bytenr); ASSERT(block_group); if (!block_group) return 0; ret = block_group->global_root_id; btrfs_put_block_group(block_group); return ret; } struct btrfs_root *btrfs_csum_root(struct btrfs_fs_info *fs_info, u64 bytenr) { struct btrfs_key key = { .objectid = BTRFS_CSUM_TREE_OBJECTID, .type = BTRFS_ROOT_ITEM_KEY, .offset = btrfs_global_root_id(fs_info, bytenr), }; return btrfs_global_root(fs_info, &key); } struct btrfs_root *btrfs_extent_root(struct btrfs_fs_info *fs_info, u64 bytenr) { struct btrfs_key key = { .objectid = BTRFS_EXTENT_TREE_OBJECTID, .type = BTRFS_ROOT_ITEM_KEY, .offset = btrfs_global_root_id(fs_info, bytenr), }; return btrfs_global_root(fs_info, &key); } struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, u64 objectid) { struct btrfs_fs_info *fs_info = trans->fs_info; struct extent_buffer *leaf; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *root; struct btrfs_key key; unsigned int nofs_flag; int ret = 0; /* * We're holding a transaction handle, so use a NOFS memory allocation * context to avoid deadlock if reclaim happens. */ nofs_flag = memalloc_nofs_save(); root = btrfs_alloc_root(fs_info, objectid, GFP_KERNEL); memalloc_nofs_restore(nofs_flag); if (!root) return ERR_PTR(-ENOMEM); root->root_key.objectid = objectid; root->root_key.type = BTRFS_ROOT_ITEM_KEY; root->root_key.offset = 0; leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0, 0, BTRFS_NESTING_NORMAL); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); leaf = NULL; goto fail; } root->node = leaf; btrfs_mark_buffer_dirty(trans, leaf); root->commit_root = btrfs_root_node(root); set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); btrfs_set_root_flags(&root->root_item, 0); btrfs_set_root_limit(&root->root_item, 0); btrfs_set_root_bytenr(&root->root_item, leaf->start); btrfs_set_root_generation(&root->root_item, trans->transid); btrfs_set_root_level(&root->root_item, 0); btrfs_set_root_refs(&root->root_item, 1); btrfs_set_root_used(&root->root_item, leaf->len); btrfs_set_root_last_snapshot(&root->root_item, 0); btrfs_set_root_dirid(&root->root_item, 0); if (is_fstree(objectid)) generate_random_guid(root->root_item.uuid); else export_guid(root->root_item.uuid, &guid_null); btrfs_set_root_drop_level(&root->root_item, 0); btrfs_tree_unlock(leaf); key.objectid = objectid; key.type = BTRFS_ROOT_ITEM_KEY; key.offset = 0; ret = btrfs_insert_root(trans, tree_root, &key, &root->root_item); if (ret) goto fail; return root; fail: btrfs_put_root(root); return ERR_PTR(ret); } static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { struct btrfs_root *root; root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_NOFS); if (!root) return ERR_PTR(-ENOMEM); root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID; root->root_key.type = BTRFS_ROOT_ITEM_KEY; root->root_key.offset = BTRFS_TREE_LOG_OBJECTID; return root; } int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans, struct btrfs_root *root) { struct extent_buffer *leaf; /* * DON'T set SHAREABLE bit for log trees. * * Log trees are not exposed to user space thus can't be snapshotted, * and they go away before a real commit is actually done. * * They do store pointers to file data extents, and those reference * counts still get updated (along with back refs to the log tree). */ leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0, 0, BTRFS_NESTING_NORMAL); if (IS_ERR(leaf)) return PTR_ERR(leaf); root->node = leaf; btrfs_mark_buffer_dirty(trans, root->node); btrfs_tree_unlock(root->node); return 0; } int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { struct btrfs_root *log_root; log_root = alloc_log_tree(trans, fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); if (!btrfs_is_zoned(fs_info)) { int ret = btrfs_alloc_log_tree_node(trans, log_root); if (ret) { btrfs_put_root(log_root); return ret; } } WARN_ON(fs_info->log_root_tree); fs_info->log_root_tree = log_root; return 0; } int btrfs_add_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log_root; struct btrfs_inode_item *inode_item; int ret; log_root = alloc_log_tree(trans, fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); ret = btrfs_alloc_log_tree_node(trans, log_root); if (ret) { btrfs_put_root(log_root); return ret; } btrfs_set_root_last_trans(log_root, trans->transid); log_root->root_key.offset = btrfs_root_id(root); inode_item = &log_root->root_item.inode; btrfs_set_stack_inode_generation(inode_item, 1); btrfs_set_stack_inode_size(inode_item, 3); btrfs_set_stack_inode_nlink(inode_item, 1); btrfs_set_stack_inode_nbytes(inode_item, fs_info->nodesize); btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755); btrfs_set_root_node(&log_root->root_item, log_root->node); WARN_ON(root->log_root); root->log_root = log_root; btrfs_set_root_log_transid(root, 0); root->log_transid_committed = -1; btrfs_set_root_last_log_commit(root, 0); return 0; } static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root, struct btrfs_path *path, const struct btrfs_key *key) { struct btrfs_root *root; struct btrfs_tree_parent_check check = { 0 }; struct btrfs_fs_info *fs_info = tree_root->fs_info; u64 generation; int ret; int level; root = btrfs_alloc_root(fs_info, key->objectid, GFP_NOFS); if (!root) return ERR_PTR(-ENOMEM); ret = btrfs_find_root(tree_root, key, path, &root->root_item, &root->root_key); if (ret) { if (ret > 0) ret = -ENOENT; goto fail; } generation = btrfs_root_generation(&root->root_item); level = btrfs_root_level(&root->root_item); check.level = level; check.transid = generation; check.owner_root = key->objectid; root->node = read_tree_block(fs_info, btrfs_root_bytenr(&root->root_item), &check); if (IS_ERR(root->node)) { ret = PTR_ERR(root->node); root->node = NULL; goto fail; } if (!btrfs_buffer_uptodate(root->node, generation, 0)) { ret = -EIO; goto fail; } /* * For real fs, and not log/reloc trees, root owner must * match its root node owner */ if (!btrfs_is_testing(fs_info) && btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID && btrfs_root_id(root) != BTRFS_TREE_RELOC_OBJECTID && btrfs_root_id(root) != btrfs_header_owner(root->node)) { btrfs_crit(fs_info, "root=%llu block=%llu, tree root owner mismatch, have %llu expect %llu", btrfs_root_id(root), root->node->start, btrfs_header_owner(root->node), btrfs_root_id(root)); ret = -EUCLEAN; goto fail; } root->commit_root = btrfs_root_node(root); return root; fail: btrfs_put_root(root); return ERR_PTR(ret); } struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, const struct btrfs_key *key) { struct btrfs_root *root; struct btrfs_path *path; path = btrfs_alloc_path(); if (!path) return ERR_PTR(-ENOMEM); root = read_tree_root_path(tree_root, path, key); btrfs_free_path(path); return root; } /* * Initialize subvolume root in-memory structure * * @anon_dev: anonymous device to attach to the root, if zero, allocate new */ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) { int ret; btrfs_drew_lock_init(&root->snapshot_lock); if (btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID && !btrfs_is_data_reloc_root(root) && is_fstree(btrfs_root_id(root))) { set_bit(BTRFS_ROOT_SHAREABLE, &root->state); btrfs_check_and_init_root_item(&root->root_item); } /* * Don't assign anonymous block device to roots that are not exposed to * userspace, the id pool is limited to 1M */ if (is_fstree(btrfs_root_id(root)) && btrfs_root_refs(&root->root_item) > 0) { if (!anon_dev) { ret = get_anon_bdev(&root->anon_dev); if (ret) goto fail; } else { root->anon_dev = anon_dev; } } mutex_lock(&root->objectid_mutex); ret = btrfs_init_root_free_objectid(root); if (ret) { mutex_unlock(&root->objectid_mutex); goto fail; } ASSERT(root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); mutex_unlock(&root->objectid_mutex); return 0; fail: /* The caller is responsible to call btrfs_free_fs_root */ return ret; } static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, u64 root_id) { struct btrfs_root *root; spin_lock(&fs_info->fs_roots_radix_lock); root = radix_tree_lookup(&fs_info->fs_roots_radix, (unsigned long)root_id); root = btrfs_grab_root(root); spin_unlock(&fs_info->fs_roots_radix_lock); return root; } static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info, u64 objectid) { struct btrfs_key key = { .objectid = objectid, .type = BTRFS_ROOT_ITEM_KEY, .offset = 0, }; switch (objectid) { case BTRFS_ROOT_TREE_OBJECTID: return btrfs_grab_root(fs_info->tree_root); case BTRFS_EXTENT_TREE_OBJECTID: return btrfs_grab_root(btrfs_global_root(fs_info, &key)); case BTRFS_CHUNK_TREE_OBJECTID: return btrfs_grab_root(fs_info->chunk_root); case BTRFS_DEV_TREE_OBJECTID: return btrfs_grab_root(fs_info->dev_root); case BTRFS_CSUM_TREE_OBJECTID: return btrfs_grab_root(btrfs_global_root(fs_info, &key)); case BTRFS_QUOTA_TREE_OBJECTID: return btrfs_grab_root(fs_info->quota_root); case BTRFS_UUID_TREE_OBJECTID: return btrfs_grab_root(fs_info->uuid_root); case BTRFS_BLOCK_GROUP_TREE_OBJECTID: return btrfs_grab_root(fs_info->block_group_root); case BTRFS_FREE_SPACE_TREE_OBJECTID: return btrfs_grab_root(btrfs_global_root(fs_info, &key)); case BTRFS_RAID_STRIPE_TREE_OBJECTID: return btrfs_grab_root(fs_info->stripe_root); default: return NULL; } } int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) { int ret; ret = radix_tree_preload(GFP_NOFS); if (ret) return ret; spin_lock(&fs_info->fs_roots_radix_lock); ret = radix_tree_insert(&fs_info->fs_roots_radix, (unsigned long)btrfs_root_id(root), root); if (ret == 0) { btrfs_grab_root(root); set_bit(BTRFS_ROOT_IN_RADIX, &root->state); } spin_unlock(&fs_info->fs_roots_radix_lock); radix_tree_preload_end(); return ret; } void btrfs_check_leaked_roots(const struct btrfs_fs_info *fs_info) { #ifdef CONFIG_BTRFS_DEBUG struct btrfs_root *root; while (!list_empty(&fs_info->allocated_roots)) { char buf[BTRFS_ROOT_NAME_BUF_LEN]; root = list_first_entry(&fs_info->allocated_roots, struct btrfs_root, leak_list); btrfs_err(fs_info, "leaked root %s refcount %d", btrfs_root_name(&root->root_key, buf), refcount_read(&root->refs)); WARN_ON_ONCE(1); while (refcount_read(&root->refs) > 1) btrfs_put_root(root); btrfs_put_root(root); } #endif } static void free_global_roots(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; struct rb_node *node; while ((node = rb_first_postorder(&fs_info->global_root_tree)) != NULL) { root = rb_entry(node, struct btrfs_root, rb_node); rb_erase(&root->rb_node, &fs_info->global_root_tree); btrfs_put_root(root); } } void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) { struct percpu_counter *em_counter = &fs_info->evictable_extent_maps; percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); percpu_counter_destroy(&fs_info->ordered_bytes); if (percpu_counter_initialized(em_counter)) ASSERT(percpu_counter_sum_positive(em_counter) == 0); percpu_counter_destroy(em_counter); percpu_counter_destroy(&fs_info->dev_replace.bio_counter); btrfs_free_csum_hash(fs_info); btrfs_free_stripe_hash_table(fs_info); btrfs_free_ref_cache(fs_info); kfree(fs_info->balance_ctl); kfree(fs_info->delayed_root); free_global_roots(fs_info); btrfs_put_root(fs_info->tree_root); btrfs_put_root(fs_info->chunk_root); btrfs_put_root(fs_info->dev_root); btrfs_put_root(fs_info->quota_root); btrfs_put_root(fs_info->uuid_root); btrfs_put_root(fs_info->fs_root); btrfs_put_root(fs_info->data_reloc_root); btrfs_put_root(fs_info->block_group_root); btrfs_put_root(fs_info->stripe_root); btrfs_check_leaked_roots(fs_info); btrfs_extent_buffer_leak_debug_check(fs_info); kfree(fs_info->super_copy); kfree(fs_info->super_for_commit); kfree(fs_info->subpage_info); kvfree(fs_info); } /* * Get an in-memory reference of a root structure. * * For essential trees like root/extent tree, we grab it from fs_info directly. * For subvolume trees, we check the cached filesystem roots first. If not * found, then read it from disk and add it to cached fs roots. * * Caller should release the root by calling btrfs_put_root() after the usage. * * NOTE: Reloc and log trees can't be read by this function as they share the * same root objectid. * * @objectid: root id * @anon_dev: preallocated anonymous block device number for new roots, * pass NULL for a new allocation. * @check_ref: whether to check root item references, If true, return -ENOENT * for orphan roots */ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, u64 objectid, dev_t *anon_dev, bool check_ref) { struct btrfs_root *root; struct btrfs_path *path; struct btrfs_key key; int ret; root = btrfs_get_global_root(fs_info, objectid); if (root) return root; /* * If we're called for non-subvolume trees, and above function didn't * find one, do not try to read it from disk. * * This is namely for free-space-tree and quota tree, which can change * at runtime and should only be grabbed from fs_info. */ if (!is_fstree(objectid) && objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) return ERR_PTR(-ENOENT); again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { /* * Some other caller may have read out the newly inserted * subvolume already (for things like backref walk etc). Not * that common but still possible. In that case, we just need * to free the anon_dev. */ if (unlikely(anon_dev && *anon_dev)) { free_anon_bdev(*anon_dev); *anon_dev = 0; } if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); } return root; } key.objectid = objectid; key.type = BTRFS_ROOT_ITEM_KEY; key.offset = (u64)-1; root = btrfs_read_tree_root(fs_info->tree_root, &key); if (IS_ERR(root)) return root; if (check_ref && btrfs_root_refs(&root->root_item) == 0) { ret = -ENOENT; goto fail; } ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0); if (ret) goto fail; path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto fail; } key.objectid = BTRFS_ORPHAN_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; key.offset = objectid; ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); btrfs_free_path(path); if (ret < 0) goto fail; if (ret == 0) set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); ret = btrfs_insert_fs_root(fs_info, root); if (ret) { if (ret == -EEXIST) { btrfs_put_root(root); goto again; } goto fail; } return root; fail: /* * If our caller provided us an anonymous device, then it's his * responsibility to free it in case we fail. So we have to set our * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() * and once again by our caller. */ if (anon_dev && *anon_dev) root->anon_dev = 0; btrfs_put_root(root); return ERR_PTR(ret); } /* * Get in-memory reference of a root structure * * @objectid: tree objectid * @check_ref: if set, verify that the tree exists and the item has at least * one reference */ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref) { return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref); } /* * Get in-memory reference of a root structure, created as new, optionally pass * the anonymous block device id * * @objectid: tree objectid * @anon_dev: if NULL, allocate a new anonymous block device or use the * parameter value if not NULL */ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, dev_t *anon_dev) { return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); } /* * Return a root for the given objectid. * * @fs_info: the fs_info * @objectid: the objectid we need to lookup * * This is exclusively used for backref walking, and exists specifically because * of how qgroups does lookups. Qgroups will do a backref lookup at delayed ref * creation time, which means we may have to read the tree_root in order to look * up a fs root that is not in memory. If the root is not in memory we will * read the tree root commit root and look up the fs root from there. This is a * temporary root, it will not be inserted into the radix tree as it doesn't * have the most uptodate information, it'll simply be discarded once the * backref code is finished using the root. */ struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 objectid) { struct btrfs_root *root; struct btrfs_key key; ASSERT(path->search_commit_root && path->skip_locking); /* * This can return -ENOENT if we ask for a root that doesn't exist, but * since this is called via the backref walking code we won't be looking * up a root that doesn't exist, unless there's corruption. So if root * != NULL just return it. */ root = btrfs_get_global_root(fs_info, objectid); if (root) return root; root = btrfs_lookup_fs_root(fs_info, objectid); if (root) return root; key.objectid = objectid; key.type = BTRFS_ROOT_ITEM_KEY; key.offset = (u64)-1; root = read_tree_root_path(fs_info->tree_root, path, &key); btrfs_release_path(path); return root; } static int cleaner_kthread(void *arg) { struct btrfs_fs_info *fs_info = arg; int again; while (1) { again = 0; set_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); /* Make the cleaner go to sleep early. */ if (btrfs_need_cleaner_sleep(fs_info)) goto sleep; /* * Do not do anything if we might cause open_ctree() to block * before we have finished mounting the filesystem. */ if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) goto sleep; if (!mutex_trylock(&fs_info->cleaner_mutex)) goto sleep; /* * Avoid the problem that we change the status of the fs * during the above check and trylock. */ if (btrfs_need_cleaner_sleep(fs_info)) { mutex_unlock(&fs_info->cleaner_mutex); goto sleep; } if (test_and_clear_bit(BTRFS_FS_FEATURE_CHANGED, &fs_info->flags)) btrfs_sysfs_feature_update(fs_info); btrfs_run_delayed_iputs(fs_info); again = btrfs_clean_one_deleted_snapshot(fs_info); mutex_unlock(&fs_info->cleaner_mutex); /* * The defragger has dealt with the R/O remount and umount, * needn't do anything special here. */ btrfs_run_defrag_inodes(fs_info); /* * Acquires fs_info->reclaim_bgs_lock to avoid racing * with relocation (btrfs_relocate_chunk) and relocation * acquires fs_info->cleaner_mutex (btrfs_relocate_block_group) * after acquiring fs_info->reclaim_bgs_lock. So we * can't hold, nor need to, fs_info->cleaner_mutex when deleting * unused block groups. */ btrfs_delete_unused_bgs(fs_info); /* * Reclaim block groups in the reclaim_bgs list after we deleted * all unused block_groups. This possibly gives us some more free * space. */ btrfs_reclaim_bgs(fs_info); sleep: clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); if (kthread_should_park()) kthread_parkme(); if (kthread_should_stop()) return 0; if (!again) { set_current_state(TASK_INTERRUPTIBLE); schedule(); __set_current_state(TASK_RUNNING); } } } static int transaction_kthread(void *arg) { struct btrfs_root *root = arg; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_trans_handle *trans; struct btrfs_transaction *cur; u64 transid; time64_t delta; unsigned long delay; bool cannot_commit; do { cannot_commit = false; delay = msecs_to_jiffies(fs_info->commit_interval * 1000); mutex_lock(&fs_info->transaction_kthread_mutex); spin_lock(&fs_info->trans_lock); cur = fs_info->running_transaction; if (!cur) { spin_unlock(&fs_info->trans_lock); goto sleep; } delta = ktime_get_seconds() - cur->start_time; if (!test_and_clear_bit(BTRFS_FS_COMMIT_TRANS, &fs_info->flags) && cur->state < TRANS_STATE_COMMIT_PREP && delta < fs_info->commit_interval) { spin_unlock(&fs_info->trans_lock); delay -= msecs_to_jiffies((delta - 1) * 1000); delay = min(delay, msecs_to_jiffies(fs_info->commit_interval * 1000)); goto sleep; } transid = cur->transid; spin_unlock(&fs_info->trans_lock); /* If the file system is aborted, this will always fail. */ trans = btrfs_attach_transaction(root); if (IS_ERR(trans)) { if (PTR_ERR(trans) != -ENOENT) cannot_commit = true; goto sleep; } if (transid == trans->transid) { btrfs_commit_transaction(trans); } else { btrfs_end_transaction(trans); } sleep: wake_up_process(fs_info->cleaner_kthread); mutex_unlock(&fs_info->transaction_kthread_mutex); if (BTRFS_FS_ERROR(fs_info)) btrfs_cleanup_transaction(fs_info); if (!kthread_should_stop() && (!btrfs_transaction_blocked(fs_info) || cannot_commit)) schedule_timeout_interruptible(delay); } while (!kthread_should_stop()); return 0; } /* * This will find the highest generation in the array of root backups. The * index of the highest array is returned, or -EINVAL if we can't find * anything. * * We check to make sure the array is valid by comparing the * generation of the latest root in the array with the generation * in the super block. If they don't match we pitch it. */ static int find_newest_super_backup(struct btrfs_fs_info *info) { const u64 newest_gen = btrfs_super_generation(info->super_copy); u64 cur; struct btrfs_root_backup *root_backup; int i; for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) { root_backup = info->super_copy->super_roots + i; cur = btrfs_backup_tree_root_gen(root_backup); if (cur == newest_gen) return i; } return -EINVAL; } /* * copy all the root pointers into the super backup array. * this will bump the backup pointer by one when it is * done */ static void backup_super_roots(struct btrfs_fs_info *info) { const int next_backup = info->backup_root_index; struct btrfs_root_backup *root_backup; root_backup = info->super_for_commit->super_roots + next_backup; /* * make sure all of our padding and empty slots get zero filled * regardless of which ones we use today */ memset(root_backup, 0, sizeof(*root_backup)); info->backup_root_index = (next_backup + 1) % BTRFS_NUM_BACKUP_ROOTS; btrfs_set_backup_tree_root(root_backup, info->tree_root->node->start); btrfs_set_backup_tree_root_gen(root_backup, btrfs_header_generation(info->tree_root->node)); btrfs_set_backup_tree_root_level(root_backup, btrfs_header_level(info->tree_root->node)); btrfs_set_backup_chunk_root(root_backup, info->chunk_root->node->start); btrfs_set_backup_chunk_root_gen(root_backup, btrfs_header_generation(info->chunk_root->node)); btrfs_set_backup_chunk_root_level(root_backup, btrfs_header_level(info->chunk_root->node)); if (!btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE)) { struct btrfs_root *extent_root = btrfs_extent_root(info, 0); struct btrfs_root *csum_root = btrfs_csum_root(info, 0); btrfs_set_backup_extent_root(root_backup, extent_root->node->start); btrfs_set_backup_extent_root_gen(root_backup, btrfs_header_generation(extent_root->node)); btrfs_set_backup_extent_root_level(root_backup, btrfs_header_level(extent_root->node)); btrfs_set_backup_csum_root(root_backup, csum_root->node->start); btrfs_set_backup_csum_root_gen(root_backup, btrfs_header_generation(csum_root->node)); btrfs_set_backup_csum_root_level(root_backup, btrfs_header_level(csum_root->node)); } /* * we might commit during log recovery, which happens before we set * the fs_root. Make sure it is valid before we fill it in. */ if (info->fs_root && info->fs_root->node) { btrfs_set_backup_fs_root(root_backup, info->fs_root->node->start); btrfs_set_backup_fs_root_gen(root_backup, btrfs_header_generation(info->fs_root->node)); btrfs_set_backup_fs_root_level(root_backup, btrfs_header_level(info->fs_root->node)); } btrfs_set_backup_dev_root(root_backup, info->dev_root->node->start); btrfs_set_backup_dev_root_gen(root_backup, btrfs_header_generation(info->dev_root->node)); btrfs_set_backup_dev_root_level(root_backup, btrfs_header_level(info->dev_root->node)); btrfs_set_backup_total_bytes(root_backup, btrfs_super_total_bytes(info->super_copy)); btrfs_set_backup_bytes_used(root_backup, btrfs_super_bytes_used(info->super_copy)); btrfs_set_backup_num_devices(root_backup, btrfs_super_num_devices(info->super_copy)); /* * if we don't copy this out to the super_copy, it won't get remembered * for the next commit */ memcpy(&info->super_copy->super_roots, &info->super_for_commit->super_roots, sizeof(*root_backup) * BTRFS_NUM_BACKUP_ROOTS); } /* * Reads a backup root based on the passed priority. Prio 0 is the newest, prio * 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots * * @fs_info: filesystem whose backup roots need to be read * @priority: priority of backup root required * * Returns backup root index on success and -EINVAL otherwise. */ static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority) { int backup_index = find_newest_super_backup(fs_info); struct btrfs_super_block *super = fs_info->super_copy; struct btrfs_root_backup *root_backup; if (priority < BTRFS_NUM_BACKUP_ROOTS && backup_index >= 0) { if (priority == 0) return backup_index; backup_index = backup_index + BTRFS_NUM_BACKUP_ROOTS - priority; backup_index %= BTRFS_NUM_BACKUP_ROOTS; } else { return -EINVAL; } root_backup = super->super_roots + backup_index; btrfs_set_super_generation(super, btrfs_backup_tree_root_gen(root_backup)); btrfs_set_super_root(super, btrfs_backup_tree_root(root_backup)); btrfs_set_super_root_level(super, btrfs_backup_tree_root_level(root_backup)); btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup)); /* * Fixme: the total bytes and num_devices need to match or we should * need a fsck */ btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup)); btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup)); return backup_index; } /* helper to cleanup workers */ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) { btrfs_destroy_workqueue(fs_info->fixup_workers); btrfs_destroy_workqueue(fs_info->delalloc_workers); btrfs_destroy_workqueue(fs_info->workers); if (fs_info->endio_workers) destroy_workqueue(fs_info->endio_workers); if (fs_info->rmw_workers) destroy_workqueue(fs_info->rmw_workers); if (fs_info->compressed_write_workers) destroy_workqueue(fs_info->compressed_write_workers); btrfs_destroy_workqueue(fs_info->endio_write_workers); btrfs_destroy_workqueue(fs_info->endio_freespace_worker); btrfs_destroy_workqueue(fs_info->delayed_workers); btrfs_destroy_workqueue(fs_info->caching_workers); btrfs_destroy_workqueue(fs_info->flush_workers); btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers); if (fs_info->discard_ctl.discard_workers) destroy_workqueue(fs_info->discard_ctl.discard_workers); /* * Now that all other work queues are destroyed, we can safely destroy * the queues used for metadata I/O, since tasks from those other work * queues can do metadata I/O operations. */ if (fs_info->endio_meta_workers) destroy_workqueue(fs_info->endio_meta_workers); } static void free_root_extent_buffers(struct btrfs_root *root) { if (root) { free_extent_buffer(root->node); free_extent_buffer(root->commit_root); root->node = NULL; root->commit_root = NULL; } } static void free_global_root_pointers(struct btrfs_fs_info *fs_info) { struct btrfs_root *root, *tmp; rbtree_postorder_for_each_entry_safe(root, tmp, &fs_info->global_root_tree, rb_node) free_root_extent_buffers(root); } /* helper to cleanup tree roots */ static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root) { free_root_extent_buffers(info->tree_root); free_global_root_pointers(info); free_root_extent_buffers(info->dev_root); free_root_extent_buffers(info->quota_root); free_root_extent_buffers(info->uuid_root); free_root_extent_buffers(info->fs_root); free_root_extent_buffers(info->data_reloc_root); free_root_extent_buffers(info->block_group_root); free_root_extent_buffers(info->stripe_root); if (free_chunk_root) free_root_extent_buffers(info->chunk_root); } void btrfs_put_root(struct btrfs_root *root) { if (!root) return; if (refcount_dec_and_test(&root->refs)) { if (WARN_ON(!xa_empty(&root->inodes))) xa_destroy(&root->inodes); WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state)); if (root->anon_dev) free_anon_bdev(root->anon_dev); free_root_extent_buffers(root); #ifdef CONFIG_BTRFS_DEBUG spin_lock(&root->fs_info->fs_roots_radix_lock); list_del_init(&root->leak_list); spin_unlock(&root->fs_info->fs_roots_radix_lock); #endif kfree(root); } } void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) { int ret; struct btrfs_root *gang[8]; int i; while (!list_empty(&fs_info->dead_roots)) { gang[0] = list_entry(fs_info->dead_roots.next, struct btrfs_root, root_list); list_del(&gang[0]->root_list); if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state)) btrfs_drop_and_free_fs_root(fs_info, gang[0]); btrfs_put_root(gang[0]); } while (1) { ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, (void **)gang, 0, ARRAY_SIZE(gang)); if (!ret) break; for (i = 0; i < ret; i++) btrfs_drop_and_free_fs_root(fs_info, gang[i]); } } static void btrfs_init_scrub(struct btrfs_fs_info *fs_info) { mutex_init(&fs_info->scrub_lock); atomic_set(&fs_info->scrubs_running, 0); atomic_set(&fs_info->scrub_pause_req, 0); atomic_set(&fs_info->scrubs_paused, 0); atomic_set(&fs_info->scrub_cancel_req, 0); init_waitqueue_head(&fs_info->scrub_pause_wait); refcount_set(&fs_info->scrub_workers_refcnt, 0); } static void btrfs_init_balance(struct btrfs_fs_info *fs_info) { spin_lock_init(&fs_info->balance_lock); mutex_init(&fs_info->balance_mutex); atomic_set(&fs_info->balance_pause_req, 0); atomic_set(&fs_info->balance_cancel_req, 0); fs_info->balance_ctl = NULL; init_waitqueue_head(&fs_info->balance_wait_q); atomic_set(&fs_info->reloc_cancel_req, 0); } static int btrfs_init_btree_inode(struct super_block *sb) { struct btrfs_fs_info *fs_info = btrfs_sb(sb); unsigned long hash = btrfs_inode_hash(BTRFS_BTREE_INODE_OBJECTID, fs_info->tree_root); struct inode *inode; inode = new_inode(sb); if (!inode) return -ENOMEM; btrfs_set_inode_number(BTRFS_I(inode), BTRFS_BTREE_INODE_OBJECTID); set_nlink(inode, 1); /* * we set the i_size on the btree inode to the max possible int. * the real end of the address space is determined by all of * the devices in the system */ inode->i_size = OFFSET_MAX; inode->i_mapping->a_ops = &btree_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree, IO_TREE_BTREE_INODE_IO); extent_map_tree_init(&BTRFS_I(inode)->extent_tree); BTRFS_I(inode)->root = btrfs_grab_root(fs_info->tree_root); set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags); __insert_inode_hash(inode, hash); fs_info->btree_inode = inode; return 0; } static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info) { mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount); init_rwsem(&fs_info->dev_replace.rwsem); init_waitqueue_head(&fs_info->dev_replace.replace_wait); } static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) { spin_lock_init(&fs_info->qgroup_lock); mutex_init(&fs_info->qgroup_ioctl_lock); fs_info->qgroup_tree = RB_ROOT; INIT_LIST_HEAD(&fs_info->dirty_qgroups); fs_info->qgroup_seq = 1; fs_info->qgroup_ulist = NULL; fs_info->qgroup_rescan_running = false; fs_info->qgroup_drop_subtree_thres = BTRFS_MAX_LEVEL; mutex_init(&fs_info->qgroup_rescan_lock); } static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info) { u32 max_active = fs_info->thread_pool_size; unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND; unsigned int ordered_flags = WQ_MEM_RECLAIM | WQ_FREEZABLE; fs_info->workers = btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16); fs_info->delalloc_workers = btrfs_alloc_workqueue(fs_info, "delalloc", flags, max_active, 2); fs_info->flush_workers = btrfs_alloc_workqueue(fs_info, "flush_delalloc", flags, max_active, 0); fs_info->caching_workers = btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0); fs_info->fixup_workers = btrfs_alloc_ordered_workqueue(fs_info, "fixup", ordered_flags); fs_info->endio_workers = alloc_workqueue("btrfs-endio", flags, max_active); fs_info->endio_meta_workers = alloc_workqueue("btrfs-endio-meta", flags, max_active); fs_info->rmw_workers = alloc_workqueue("btrfs-rmw", flags, max_active); fs_info->endio_write_workers = btrfs_alloc_workqueue(fs_info, "endio-write", flags, max_active, 2); fs_info->compressed_write_workers = alloc_workqueue("btrfs-compressed-write", flags, max_active); fs_info->endio_freespace_worker = btrfs_alloc_workqueue(fs_info, "freespace-write", flags, max_active, 0); fs_info->delayed_workers = btrfs_alloc_workqueue(fs_info, "delayed-meta", flags, max_active, 0); fs_info->qgroup_rescan_workers = btrfs_alloc_ordered_workqueue(fs_info, "qgroup-rescan", ordered_flags); fs_info->discard_ctl.discard_workers = alloc_ordered_workqueue("btrfs_discard", WQ_FREEZABLE); if (!(fs_info->workers && fs_info->delalloc_workers && fs_info->flush_workers && fs_info->endio_workers && fs_info->endio_meta_workers && fs_info->compressed_write_workers && fs_info->endio_write_workers && fs_info->endio_freespace_worker && fs_info->rmw_workers && fs_info->caching_workers && fs_info->fixup_workers && fs_info->delayed_workers && fs_info->qgroup_rescan_workers && fs_info->discard_ctl.discard_workers)) { return -ENOMEM; } return 0; } static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) { struct crypto_shash *csum_shash; const char *csum_driver = btrfs_super_csum_driver(csum_type); csum_shash = crypto_alloc_shash(csum_driver, 0, 0); if (IS_ERR(csum_shash)) { btrfs_err(fs_info, "error allocating %s hash for checksum", csum_driver); return PTR_ERR(csum_shash); } fs_info->csum_shash = csum_shash; /* * Check if the checksum implementation is a fast accelerated one. * As-is this is a bit of a hack and should be replaced once the csum * implementations provide that information themselves. */ switch (csum_type) { case BTRFS_CSUM_TYPE_CRC32: if (!strstr(crypto_shash_driver_name(csum_shash), "generic")) set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); break; case BTRFS_CSUM_TYPE_XXHASH: set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); break; default: break; } btrfs_info(fs_info, "using %s (%s) checksum algorithm", btrfs_super_csum_name(csum_type), crypto_shash_driver_name(csum_shash)); return 0; } static int btrfs_replay_log(struct btrfs_fs_info *fs_info, struct btrfs_fs_devices *fs_devices) { int ret; struct btrfs_tree_parent_check check = { 0 }; struct btrfs_root *log_tree_root; struct btrfs_super_block *disk_super = fs_info->super_copy; u64 bytenr = btrfs_super_log_root(disk_super); int level = btrfs_super_log_root_level(disk_super); if (fs_devices->rw_devices == 0) { btrfs_warn(fs_info, "log replay required on RO media"); return -EIO; } log_tree_root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_KERNEL); if (!log_tree_root) return -ENOMEM; check.level = level; check.transid = fs_info->generation + 1; check.owner_root = BTRFS_TREE_LOG_OBJECTID; log_tree_root->node = read_tree_block(fs_info, bytenr, &check); if (IS_ERR(log_tree_root->node)) { btrfs_warn(fs_info, "failed to read log tree"); ret = PTR_ERR(log_tree_root->node); log_tree_root->node = NULL; btrfs_put_root(log_tree_root); return ret; } if (!extent_buffer_uptodate(log_tree_root->node)) { btrfs_err(fs_info, "failed to read log tree"); btrfs_put_root(log_tree_root); return -EIO; } /* returns with log_tree_root freed on success */ ret = btrfs_recover_log_trees(log_tree_root); if (ret) { btrfs_handle_fs_error(fs_info, ret, "Failed to recover log tree"); btrfs_put_root(log_tree_root); return ret; } if (sb_rdonly(fs_info->sb)) { ret = btrfs_commit_super(fs_info); if (ret) return ret; } return 0; } static int load_global_roots_objectid(struct btrfs_root *tree_root, struct btrfs_path *path, u64 objectid, const char *name) { struct btrfs_fs_info *fs_info = tree_root->fs_info; struct btrfs_root *root; u64 max_global_id = 0; int ret; struct btrfs_key key = { .objectid = objectid, .type = BTRFS_ROOT_ITEM_KEY, .offset = 0, }; bool found = false; /* If we have IGNOREDATACSUMS skip loading these roots. */ if (objectid == BTRFS_CSUM_TREE_OBJECTID && btrfs_test_opt(fs_info, IGNOREDATACSUMS)) { set_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state); return 0; } while (1) { ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0); if (ret < 0) break; if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { ret = btrfs_next_leaf(tree_root, path); if (ret) { if (ret > 0) ret = 0; break; } } ret = 0; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid != objectid) break; btrfs_release_path(path); /* * Just worry about this for extent tree, it'll be the same for * everybody. */ if (objectid == BTRFS_EXTENT_TREE_OBJECTID) max_global_id = max(max_global_id, key.offset); found = true; root = read_tree_root_path(tree_root, path, &key); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) ret = PTR_ERR(root); break; } set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); ret = btrfs_global_root_insert(root); if (ret) { btrfs_put_root(root); break; } key.offset++; } btrfs_release_path(path); if (objectid == BTRFS_EXTENT_TREE_OBJECTID) fs_info->nr_global_roots = max_global_id + 1; if (!found || ret) { if (objectid == BTRFS_CSUM_TREE_OBJECTID) set_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state); if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) ret = ret ? ret : -ENOENT; else ret = 0; btrfs_err(fs_info, "failed to load root %s", name); } return ret; } static int load_global_roots(struct btrfs_root *tree_root) { struct btrfs_path *path; int ret = 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = load_global_roots_objectid(tree_root, path, BTRFS_EXTENT_TREE_OBJECTID, "extent"); if (ret) goto out; ret = load_global_roots_objectid(tree_root, path, BTRFS_CSUM_TREE_OBJECTID, "csum"); if (ret) goto out; if (!btrfs_fs_compat_ro(tree_root->fs_info, FREE_SPACE_TREE)) goto out; ret = load_global_roots_objectid(tree_root, path, BTRFS_FREE_SPACE_TREE_OBJECTID, "free space"); out: btrfs_free_path(path); return ret; } static int btrfs_read_roots(struct btrfs_fs_info *fs_info) { struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *root; struct btrfs_key location; int ret; ASSERT(fs_info->tree_root); ret = load_global_roots(tree_root); if (ret) return ret; location.type = BTRFS_ROOT_ITEM_KEY; location.offset = 0; if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE)) { location.objectid = BTRFS_BLOCK_GROUP_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { ret = PTR_ERR(root); goto out; } } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->block_group_root = root; } } location.objectid = BTRFS_DEV_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { ret = PTR_ERR(root); goto out; } } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->dev_root = root; } /* Initialize fs_info for all devices in any case */ ret = btrfs_init_devices_late(fs_info); if (ret) goto out; /* * This tree can share blocks with some other fs tree during relocation * and we need a proper setup by btrfs_get_fs_root */ root = btrfs_get_fs_root(tree_root->fs_info, BTRFS_DATA_RELOC_TREE_OBJECTID, true); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { ret = PTR_ERR(root); goto out; } } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->data_reloc_root = root; } location.objectid = BTRFS_QUOTA_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (!IS_ERR(root)) { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->quota_root = root; } location.objectid = BTRFS_UUID_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { ret = PTR_ERR(root); if (ret != -ENOENT) goto out; } } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->uuid_root = root; } if (btrfs_fs_incompat(fs_info, RAID_STRIPE_TREE)) { location.objectid = BTRFS_RAID_STRIPE_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { ret = PTR_ERR(root); goto out; } } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->stripe_root = root; } } return 0; out: btrfs_warn(fs_info, "failed to read root (objectid=%llu): %d", location.objectid, ret); return ret; } /* * Real super block validation * NOTE: super csum type and incompat features will not be checked here. * * @sb: super block to check * @mirror_num: the super block number to check its bytenr: * 0 the primary (1st) sb * 1, 2 2nd and 3rd backup copy * -1 skip bytenr check */ int btrfs_validate_super(const struct btrfs_fs_info *fs_info, const struct btrfs_super_block *sb, int mirror_num) { u64 nodesize = btrfs_super_nodesize(sb); u64 sectorsize = btrfs_super_sectorsize(sb); int ret = 0; const bool ignore_flags = btrfs_test_opt(fs_info, IGNORESUPERFLAGS); if (btrfs_super_magic(sb) != BTRFS_MAGIC) { btrfs_err(fs_info, "no valid FS found"); ret = -EINVAL; } if ((btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP)) { if (!ignore_flags) { btrfs_err(fs_info, "unrecognized or unsupported super flag 0x%llx", btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP); ret = -EINVAL; } else { btrfs_info(fs_info, "unrecognized or unsupported super flags: 0x%llx, ignored", btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP); } } if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) { btrfs_err(fs_info, "tree_root level too big: %d >= %d", btrfs_super_root_level(sb), BTRFS_MAX_LEVEL); ret = -EINVAL; } if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) { btrfs_err(fs_info, "chunk_root level too big: %d >= %d", btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL); ret = -EINVAL; } if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) { btrfs_err(fs_info, "log_root level too big: %d >= %d", btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL); ret = -EINVAL; } /* * Check sectorsize and nodesize first, other check will need it. * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here. */ if (!is_power_of_2(sectorsize) || sectorsize < 4096 || sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) { btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize); ret = -EINVAL; } /* * We only support at most two sectorsizes: 4K and PAGE_SIZE. * * We can support 16K sectorsize with 64K page size without problem, * but such sectorsize/pagesize combination doesn't make much sense. * 4K will be our future standard, PAGE_SIZE is supported from the very * beginning. */ if (sectorsize > PAGE_SIZE || (sectorsize != SZ_4K && sectorsize != PAGE_SIZE)) { btrfs_err(fs_info, "sectorsize %llu not yet supported for page size %lu", sectorsize, PAGE_SIZE); ret = -EINVAL; } if (!is_power_of_2(nodesize) || nodesize < sectorsize || nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) { btrfs_err(fs_info, "invalid nodesize %llu", nodesize); ret = -EINVAL; } if (nodesize != le32_to_cpu(sb->__unused_leafsize)) { btrfs_err(fs_info, "invalid leafsize %u, should be %llu", le32_to_cpu(sb->__unused_leafsize), nodesize); ret = -EINVAL; } /* Root alignment check */ if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) { btrfs_warn(fs_info, "tree_root block unaligned: %llu", btrfs_super_root(sb)); ret = -EINVAL; } if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) { btrfs_warn(fs_info, "chunk_root block unaligned: %llu", btrfs_super_chunk_root(sb)); ret = -EINVAL; } if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) { btrfs_warn(fs_info, "log_root block unaligned: %llu", btrfs_super_log_root(sb)); ret = -EINVAL; } if (!fs_info->fs_devices->temp_fsid && memcmp(fs_info->fs_devices->fsid, sb->fsid, BTRFS_FSID_SIZE) != 0) { btrfs_err(fs_info, "superblock fsid doesn't match fsid of fs_devices: %pU != %pU", sb->fsid, fs_info->fs_devices->fsid); ret = -EINVAL; } if (memcmp(fs_info->fs_devices->metadata_uuid, btrfs_sb_fsid_ptr(sb), BTRFS_FSID_SIZE) != 0) { btrfs_err(fs_info, "superblock metadata_uuid doesn't match metadata uuid of fs_devices: %pU != %pU", btrfs_sb_fsid_ptr(sb), fs_info->fs_devices->metadata_uuid); ret = -EINVAL; } if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) { btrfs_err(fs_info, "dev_item UUID does not match metadata fsid: %pU != %pU", fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid); ret = -EINVAL; } /* * Artificial requirement for block-group-tree to force newer features * (free-space-tree, no-holes) so the test matrix is smaller. */ if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE) && (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID) || !btrfs_fs_incompat(fs_info, NO_HOLES))) { btrfs_err(fs_info, "block-group-tree feature requires free-space-tree and no-holes"); ret = -EINVAL; } /* * Hint to catch really bogus numbers, bitflips or so, more exact checks are * done later */ if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) { btrfs_err(fs_info, "bytes_used is too small %llu", btrfs_super_bytes_used(sb)); ret = -EINVAL; } if (!is_power_of_2(btrfs_super_stripesize(sb))) { btrfs_err(fs_info, "invalid stripesize %u", btrfs_super_stripesize(sb)); ret = -EINVAL; } if (btrfs_super_num_devices(sb) > (1UL << 31)) btrfs_warn(fs_info, "suspicious number of devices: %llu", btrfs_super_num_devices(sb)); if (btrfs_super_num_devices(sb) == 0) { btrfs_err(fs_info, "number of devices is 0"); ret = -EINVAL; } if (mirror_num >= 0 && btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) { btrfs_err(fs_info, "super offset mismatch %llu != %u", btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET); ret = -EINVAL; } /* * Obvious sys_chunk_array corruptions, it must hold at least one key * and one chunk */ if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) { btrfs_err(fs_info, "system chunk array too big %u > %u", btrfs_super_sys_array_size(sb), BTRFS_SYSTEM_CHUNK_ARRAY_SIZE); ret = -EINVAL; } if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key) + sizeof(struct btrfs_chunk)) { btrfs_err(fs_info, "system chunk array too small %u < %zu", btrfs_super_sys_array_size(sb), sizeof(struct btrfs_disk_key) + sizeof(struct btrfs_chunk)); ret = -EINVAL; } /* * The generation is a global counter, we'll trust it more than the others * but it's still possible that it's the one that's wrong. */ if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb)) btrfs_warn(fs_info, "suspicious: generation < chunk_root_generation: %llu < %llu", btrfs_super_generation(sb), btrfs_super_chunk_root_generation(sb)); if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb) && btrfs_super_cache_generation(sb) != (u64)-1) btrfs_warn(fs_info, "suspicious: generation < cache_generation: %llu < %llu", btrfs_super_generation(sb), btrfs_super_cache_generation(sb)); return ret; } /* * Validation of super block at mount time. * Some checks already done early at mount time, like csum type and incompat * flags will be skipped. */ static int btrfs_validate_mount_super(struct btrfs_fs_info *fs_info) { return btrfs_validate_super(fs_info, fs_info->super_copy, 0); } /* * Validation of super block at write time. * Some checks like bytenr check will be skipped as their values will be * overwritten soon. * Extra checks like csum type and incompat flags will be done here. */ static int btrfs_validate_write_super(struct btrfs_fs_info *fs_info, struct btrfs_super_block *sb) { int ret; ret = btrfs_validate_super(fs_info, sb, -1); if (ret < 0) goto out; if (!btrfs_supported_super_csum(btrfs_super_csum_type(sb))) { ret = -EUCLEAN; btrfs_err(fs_info, "invalid csum type, has %u want %u", btrfs_super_csum_type(sb), BTRFS_CSUM_TYPE_CRC32); goto out; } if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) { ret = -EUCLEAN; btrfs_err(fs_info, "invalid incompat flags, has 0x%llx valid mask 0x%llx", btrfs_super_incompat_flags(sb), (unsigned long long)BTRFS_FEATURE_INCOMPAT_SUPP); goto out; } out: if (ret < 0) btrfs_err(fs_info, "super block corruption detected before writing it to disk"); return ret; } static int load_super_root(struct btrfs_root *root, u64 bytenr, u64 gen, int level) { struct btrfs_tree_parent_check check = { .level = level, .transid = gen, .owner_root = btrfs_root_id(root) }; int ret = 0; root->node = read_tree_block(root->fs_info, bytenr, &check); if (IS_ERR(root->node)) { ret = PTR_ERR(root->node); root->node = NULL; return ret; } if (!extent_buffer_uptodate(root->node)) { free_extent_buffer(root->node); root->node = NULL; return -EIO; } btrfs_set_root_node(&root->root_item, root->node); root->commit_root = btrfs_root_node(root); btrfs_set_root_refs(&root->root_item, 1); return ret; } static int load_important_roots(struct btrfs_fs_info *fs_info) { struct btrfs_super_block *sb = fs_info->super_copy; u64 gen, bytenr; int level, ret; bytenr = btrfs_super_root(sb); gen = btrfs_super_generation(sb); level = btrfs_super_root_level(sb); ret = load_super_root(fs_info->tree_root, bytenr, gen, level); if (ret) { btrfs_warn(fs_info, "couldn't read tree root"); return ret; } return 0; } static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) { int backup_index = find_newest_super_backup(fs_info); struct btrfs_super_block *sb = fs_info->super_copy; struct btrfs_root *tree_root = fs_info->tree_root; bool handle_error = false; int ret = 0; int i; for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) { if (handle_error) { if (!IS_ERR(tree_root->node)) free_extent_buffer(tree_root->node); tree_root->node = NULL; if (!btrfs_test_opt(fs_info, USEBACKUPROOT)) break; free_root_pointers(fs_info, 0); /* * Don't use the log in recovery mode, it won't be * valid */ btrfs_set_super_log_root(sb, 0); btrfs_warn(fs_info, "try to load backup roots slot %d", i); ret = read_backup_root(fs_info, i); backup_index = ret; if (ret < 0) return ret; } ret = load_important_roots(fs_info); if (ret) { handle_error = true; continue; } /* * No need to hold btrfs_root::objectid_mutex since the fs * hasn't been fully initialised and we are the only user */ ret = btrfs_init_root_free_objectid(tree_root); if (ret < 0) { handle_error = true; continue; } ASSERT(tree_root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); ret = btrfs_read_roots(fs_info); if (ret < 0) { handle_error = true; continue; } /* All successful */ fs_info->generation = btrfs_header_generation(tree_root->node); btrfs_set_last_trans_committed(fs_info, fs_info->generation); fs_info->last_reloc_trans = 0; /* Always begin writing backup roots after the one being used */ if (backup_index < 0) { fs_info->backup_root_index = 0; } else { fs_info->backup_root_index = backup_index + 1; fs_info->backup_root_index %= BTRFS_NUM_BACKUP_ROOTS; } break; } return ret; } void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) { INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC); INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC); INIT_LIST_HEAD(&fs_info->trans_list); INIT_LIST_HEAD(&fs_info->dead_roots); INIT_LIST_HEAD(&fs_info->delayed_iputs); INIT_LIST_HEAD(&fs_info->delalloc_roots); INIT_LIST_HEAD(&fs_info->caching_block_groups); spin_lock_init(&fs_info->delalloc_root_lock); spin_lock_init(&fs_info->trans_lock); spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->buffer_lock); spin_lock_init(&fs_info->unused_bgs_lock); spin_lock_init(&fs_info->treelog_bg_lock); spin_lock_init(&fs_info->zone_active_bgs_lock); spin_lock_init(&fs_info->relocation_bg_lock); rwlock_init(&fs_info->tree_mod_log_lock); rwlock_init(&fs_info->global_root_lock); mutex_init(&fs_info->unused_bg_unpin_mutex); mutex_init(&fs_info->reclaim_bgs_lock); mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); mutex_init(&fs_info->zoned_meta_io_lock); mutex_init(&fs_info->zoned_data_reloc_io_lock); seqlock_init(&fs_info->profiles_lock); btrfs_lockdep_init_map(fs_info, btrfs_trans_num_writers); btrfs_lockdep_init_map(fs_info, btrfs_trans_num_extwriters); btrfs_lockdep_init_map(fs_info, btrfs_trans_pending_ordered); btrfs_lockdep_init_map(fs_info, btrfs_ordered_extent); btrfs_state_lockdep_init_map(fs_info, btrfs_trans_commit_prep, BTRFS_LOCKDEP_TRANS_COMMIT_PREP); btrfs_state_lockdep_init_map(fs_info, btrfs_trans_unblocked, BTRFS_LOCKDEP_TRANS_UNBLOCKED); btrfs_state_lockdep_init_map(fs_info, btrfs_trans_super_committed, BTRFS_LOCKDEP_TRANS_SUPER_COMMITTED); btrfs_state_lockdep_init_map(fs_info, btrfs_trans_completed, BTRFS_LOCKDEP_TRANS_COMPLETED); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); INIT_LIST_HEAD(&fs_info->space_info); INIT_LIST_HEAD(&fs_info->tree_mod_seq_list); INIT_LIST_HEAD(&fs_info->unused_bgs); INIT_LIST_HEAD(&fs_info->reclaim_bgs); INIT_LIST_HEAD(&fs_info->zone_active_bgs); #ifdef CONFIG_BTRFS_DEBUG INIT_LIST_HEAD(&fs_info->allocated_roots); INIT_LIST_HEAD(&fs_info->allocated_ebs); spin_lock_init(&fs_info->eb_leak_lock); #endif fs_info->mapping_tree = RB_ROOT_CACHED; rwlock_init(&fs_info->mapping_tree_lock); btrfs_init_block_rsv(&fs_info->global_block_rsv, BTRFS_BLOCK_RSV_GLOBAL); btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS); btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK); btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY); btrfs_init_block_rsv(&fs_info->delayed_block_rsv, BTRFS_BLOCK_RSV_DELOPS); btrfs_init_block_rsv(&fs_info->delayed_refs_rsv, BTRFS_BLOCK_RSV_DELREFS); atomic_set(&fs_info->async_delalloc_pages, 0); atomic_set(&fs_info->defrag_running, 0); atomic_set(&fs_info->nr_delayed_iputs, 0); atomic64_set(&fs_info->tree_mod_seq, 0); fs_info->global_root_tree = RB_ROOT; fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE; fs_info->metadata_ratio = 0; fs_info->defrag_inodes = RB_ROOT; atomic64_set(&fs_info->free_chunk_space, 0); fs_info->tree_mod_log = RB_ROOT; fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; btrfs_init_ref_verify(fs_info); fs_info->thread_pool_size = min_t(unsigned long, num_online_cpus() + 2, 8); INIT_LIST_HEAD(&fs_info->ordered_roots); spin_lock_init(&fs_info->ordered_root_lock); btrfs_init_scrub(fs_info); btrfs_init_balance(fs_info); btrfs_init_async_reclaim_work(fs_info); rwlock_init(&fs_info->block_group_cache_lock); fs_info->block_group_cache_tree = RB_ROOT_CACHED; extent_io_tree_init(fs_info, &fs_info->excluded_extents, IO_TREE_FS_EXCLUDED_EXTENTS); mutex_init(&fs_info->ordered_operations_mutex); mutex_init(&fs_info->tree_log_mutex); mutex_init(&fs_info->chunk_mutex); mutex_init(&fs_info->transaction_kthread_mutex); mutex_init(&fs_info->cleaner_mutex); mutex_init(&fs_info->ro_block_group_mutex); init_rwsem(&fs_info->commit_root_sem); init_rwsem(&fs_info->cleanup_work_sem); init_rwsem(&fs_info->subvol_sem); sema_init(&fs_info->uuid_tree_rescan_sem, 1); btrfs_init_dev_replace_locks(fs_info); btrfs_init_qgroup(fs_info); btrfs_discard_init(fs_info); btrfs_init_free_cluster(&fs_info->meta_alloc_cluster); btrfs_init_free_cluster(&fs_info->data_alloc_cluster); init_waitqueue_head(&fs_info->transaction_throttle); init_waitqueue_head(&fs_info->transaction_wait); init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); init_waitqueue_head(&fs_info->delayed_iputs_wait); /* Usable values until the real ones are cached from the superblock */ fs_info->nodesize = 4096; fs_info->sectorsize = 4096; fs_info->sectorsize_bits = ilog2(4096); fs_info->stripesize = 4096; /* Default compress algorithm when user does -o compress */ fs_info->compress_type = BTRFS_COMPRESS_ZLIB; fs_info->max_extent_size = BTRFS_MAX_EXTENT_SIZE; spin_lock_init(&fs_info->swapfile_pins_lock); fs_info->swapfile_pins = RB_ROOT; fs_info->bg_reclaim_threshold = BTRFS_DEFAULT_RECLAIM_THRESH; INIT_WORK(&fs_info->reclaim_bgs_work, btrfs_reclaim_bgs_work); } static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block *sb) { int ret; fs_info->sb = sb; /* Temporary fixed values for block size until we read the superblock. */ sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE; sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE); ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL); if (ret) return ret; ret = percpu_counter_init(&fs_info->evictable_extent_maps, 0, GFP_KERNEL); if (ret) return ret; spin_lock_init(&fs_info->extent_map_shrinker_lock); ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL); if (ret) return ret; fs_info->dirty_metadata_batch = PAGE_SIZE * (1 + ilog2(nr_cpu_ids)); ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL); if (ret) return ret; ret = percpu_counter_init(&fs_info->dev_replace.bio_counter, 0, GFP_KERNEL); if (ret) return ret; fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root), GFP_KERNEL); if (!fs_info->delayed_root) return -ENOMEM; btrfs_init_delayed_root(fs_info->delayed_root); if (sb_rdonly(sb)) set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state); if (btrfs_test_opt(fs_info, IGNOREMETACSUMS)) set_bit(BTRFS_FS_STATE_SKIP_META_CSUMS, &fs_info->fs_state); return btrfs_alloc_stripe_hash_table(fs_info); } static int btrfs_uuid_rescan_kthread(void *data) { struct btrfs_fs_info *fs_info = data; int ret; /* * 1st step is to iterate through the existing UUID tree and * to delete all entries that contain outdated data. * 2nd step is to add all missing entries to the UUID tree. */ ret = btrfs_uuid_tree_iterate(fs_info); if (ret < 0) { if (ret != -EINTR) btrfs_warn(fs_info, "iterating uuid_tree failed %d", ret); up(&fs_info->uuid_tree_rescan_sem); return ret; } return btrfs_uuid_scan_kthread(data); } static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info) { struct task_struct *task; down(&fs_info->uuid_tree_rescan_sem); task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid"); if (IS_ERR(task)) { /* fs_info->update_uuid_tree_gen remains 0 in all error case */ btrfs_warn(fs_info, "failed to start uuid_rescan task"); up(&fs_info->uuid_tree_rescan_sem); return PTR_ERR(task); } return 0; } static int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) { u64 root_objectid = 0; struct btrfs_root *gang[8]; int ret = 0; while (1) { unsigned int found; spin_lock(&fs_info->fs_roots_radix_lock); found = radix_tree_gang_lookup(&fs_info->fs_roots_radix, (void **)gang, root_objectid, ARRAY_SIZE(gang)); if (!found) { spin_unlock(&fs_info->fs_roots_radix_lock); break; } root_objectid = btrfs_root_id(gang[found - 1]) + 1; for (int i = 0; i < found; i++) { /* Avoid to grab roots in dead_roots. */ if (btrfs_root_refs(&gang[i]->root_item) == 0) { gang[i] = NULL; continue; } /* Grab all the search result for later use. */ gang[i] = btrfs_grab_root(gang[i]); } spin_unlock(&fs_info->fs_roots_radix_lock); for (int i = 0; i < found; i++) { if (!gang[i]) continue; root_objectid = btrfs_root_id(gang[i]); /* * Continue to release the remaining roots after the first * error without cleanup and preserve the first error * for the return. */ if (!ret) ret = btrfs_orphan_cleanup(gang[i]); btrfs_put_root(gang[i]); } if (ret) break; root_objectid++; } return ret; } /* * Mounting logic specific to read-write file systems. Shared by open_ctree * and btrfs_remount when remounting from read-only to read-write. */ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) { int ret; const bool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE); bool rebuild_free_space_tree = false; if (btrfs_test_opt(fs_info, CLEAR_CACHE) && btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) btrfs_warn(fs_info, "'clear_cache' option is ignored with extent tree v2"); else rebuild_free_space_tree = true; } else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) { btrfs_warn(fs_info, "free space tree is invalid"); rebuild_free_space_tree = true; } if (rebuild_free_space_tree) { btrfs_info(fs_info, "rebuilding free space tree"); ret = btrfs_rebuild_free_space_tree(fs_info); if (ret) { btrfs_warn(fs_info, "failed to rebuild free space tree: %d", ret); goto out; } } if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && !btrfs_test_opt(fs_info, FREE_SPACE_TREE)) { btrfs_info(fs_info, "disabling free space tree"); ret = btrfs_delete_free_space_tree(fs_info); if (ret) { btrfs_warn(fs_info, "failed to disable free space tree: %d", ret); goto out; } } /* * btrfs_find_orphan_roots() is responsible for finding all the dead * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load * them into the fs_info->fs_roots_radix tree. This must be done before * calling btrfs_orphan_cleanup() on the tree root. If we don't do it * first, then btrfs_orphan_cleanup() will delete a dead root's orphan * item before the root's tree is deleted - this means that if we unmount * or crash before the deletion completes, on the next mount we will not * delete what remains of the tree because the orphan item does not * exists anymore, which is what tells us we have a pending deletion. */ ret = btrfs_find_orphan_roots(fs_info); if (ret) goto out; ret = btrfs_cleanup_fs_roots(fs_info); if (ret) goto out; down_read(&fs_info->cleanup_work_sem); if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { up_read(&fs_info->cleanup_work_sem); goto out; } up_read(&fs_info->cleanup_work_sem); mutex_lock(&fs_info->cleaner_mutex); ret = btrfs_recover_relocation(fs_info); mutex_unlock(&fs_info->cleaner_mutex); if (ret < 0) { btrfs_warn(fs_info, "failed to recover relocation: %d", ret); goto out; } if (btrfs_test_opt(fs_info, FREE_SPACE_TREE) && !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { btrfs_info(fs_info, "creating free space tree"); ret = btrfs_create_free_space_tree(fs_info); if (ret) { btrfs_warn(fs_info, "failed to create free space tree: %d", ret); goto out; } } if (cache_opt != btrfs_free_space_cache_v1_active(fs_info)) { ret = btrfs_set_free_space_cache_v1_active(fs_info, cache_opt); if (ret) goto out; } ret = btrfs_resume_balance_async(fs_info); if (ret) goto out; ret = btrfs_resume_dev_replace_async(fs_info); if (ret) { btrfs_warn(fs_info, "failed to resume dev_replace"); goto out; } btrfs_qgroup_rescan_resume(fs_info); if (!fs_info->uuid_root) { btrfs_info(fs_info, "creating UUID tree"); ret = btrfs_create_uuid_tree(fs_info); if (ret) { btrfs_warn(fs_info, "failed to create the UUID tree %d", ret); goto out; } } out: return ret; } /* * Do various sanity and dependency checks of different features. * * @is_rw_mount: If the mount is read-write. * * This is the place for less strict checks (like for subpage or artificial * feature dependencies). * * For strict checks or possible corruption detection, see * btrfs_validate_super(). * * This should be called after btrfs_parse_options(), as some mount options * (space cache related) can modify on-disk format like free space tree and * screw up certain feature dependencies. */ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) { struct btrfs_super_block *disk_super = fs_info->super_copy; u64 incompat = btrfs_super_incompat_flags(disk_super); const u64 compat_ro = btrfs_super_compat_ro_flags(disk_super); const u64 compat_ro_unsupp = (compat_ro & ~BTRFS_FEATURE_COMPAT_RO_SUPP); if (incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP) { btrfs_err(fs_info, "cannot mount because of unknown incompat features (0x%llx)", incompat); return -EINVAL; } /* Runtime limitation for mixed block groups. */ if ((incompat & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) && (fs_info->sectorsize != fs_info->nodesize)) { btrfs_err(fs_info, "unequal nodesize/sectorsize (%u != %u) are not allowed for mixed block groups", fs_info->nodesize, fs_info->sectorsize); return -EINVAL; } /* Mixed backref is an always-enabled feature. */ incompat |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; /* Set compression related flags just in case. */ if (fs_info->compress_type == BTRFS_COMPRESS_LZO) incompat |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; else if (fs_info->compress_type == BTRFS_COMPRESS_ZSTD) incompat |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD; /* * An ancient flag, which should really be marked deprecated. * Such runtime limitation doesn't really need a incompat flag. */ if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) incompat |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA; if (compat_ro_unsupp && is_rw_mount) { btrfs_err(fs_info, "cannot mount read-write because of unknown compat_ro features (0x%llx)", compat_ro); return -EINVAL; } /* * We have unsupported RO compat features, although RO mounted, we * should not cause any metadata writes, including log replay. * Or we could screw up whatever the new feature requires. */ if (compat_ro_unsupp && btrfs_super_log_root(disk_super) && !btrfs_test_opt(fs_info, NOLOGREPLAY)) { btrfs_err(fs_info, "cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay", compat_ro); return -EINVAL; } /* * Artificial limitations for block group tree, to force * block-group-tree to rely on no-holes and free-space-tree. */ if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE) && (!btrfs_fs_incompat(fs_info, NO_HOLES) || !btrfs_test_opt(fs_info, FREE_SPACE_TREE))) { btrfs_err(fs_info, "block-group-tree feature requires no-holes and free-space-tree features"); return -EINVAL; } /* * Subpage runtime limitation on v1 cache. * * V1 space cache still has some hard codeed PAGE_SIZE usage, while * we're already defaulting to v2 cache, no need to bother v1 as it's * going to be deprecated anyway. */ if (fs_info->sectorsize < PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) { btrfs_warn(fs_info, "v1 space cache is not supported for page size %lu with sectorsize %u", PAGE_SIZE, fs_info->sectorsize); return -EINVAL; } /* This can be called by remount, we need to protect the super block. */ spin_lock(&fs_info->super_lock); btrfs_set_super_incompat_flags(disk_super, incompat); spin_unlock(&fs_info->super_lock); return 0; } int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, const char *options) { u32 sectorsize; u32 nodesize; u32 stripesize; u64 generation; u16 csum_type; struct btrfs_super_block *disk_super; struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *tree_root; struct btrfs_root *chunk_root; int ret; int level; ret = init_mount_fs_info(fs_info, sb); if (ret) goto fail; /* These need to be init'ed before we start creating inodes and such. */ tree_root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID, GFP_KERNEL); fs_info->tree_root = tree_root; chunk_root = btrfs_alloc_root(fs_info, BTRFS_CHUNK_TREE_OBJECTID, GFP_KERNEL); fs_info->chunk_root = chunk_root; if (!tree_root || !chunk_root) { ret = -ENOMEM; goto fail; } ret = btrfs_init_btree_inode(sb); if (ret) goto fail; invalidate_bdev(fs_devices->latest_dev->bdev); /* * Read super block and check the signature bytes only */ disk_super = btrfs_read_dev_super(fs_devices->latest_dev->bdev); if (IS_ERR(disk_super)) { ret = PTR_ERR(disk_super); goto fail_alloc; } btrfs_info(fs_info, "first mount of filesystem %pU", disk_super->fsid); /* * Verify the type first, if that or the checksum value are * corrupted, we'll find out */ csum_type = btrfs_super_csum_type(disk_super); if (!btrfs_supported_super_csum(csum_type)) { btrfs_err(fs_info, "unsupported checksum algorithm: %u", csum_type); ret = -EINVAL; btrfs_release_disk_super(disk_super); goto fail_alloc; } fs_info->csum_size = btrfs_super_csum_size(disk_super); ret = btrfs_init_csum_hash(fs_info, csum_type); if (ret) { btrfs_release_disk_super(disk_super); goto fail_alloc; } /* * We want to check superblock checksum, the type is stored inside. * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k). */ if (btrfs_check_super_csum(fs_info, disk_super)) { btrfs_err(fs_info, "superblock checksum mismatch"); ret = -EINVAL; btrfs_release_disk_super(disk_super); goto fail_alloc; } /* * super_copy is zeroed at allocation time and we never touch the * following bytes up to INFO_SIZE, the checksum is calculated from * the whole block of INFO_SIZE */ memcpy(fs_info->super_copy, disk_super, sizeof(*fs_info->super_copy)); btrfs_release_disk_super(disk_super); disk_super = fs_info->super_copy; memcpy(fs_info->super_for_commit, fs_info->super_copy, sizeof(*fs_info->super_for_commit)); ret = btrfs_validate_mount_super(fs_info); if (ret) { btrfs_err(fs_info, "superblock contains fatal errors"); ret = -EINVAL; goto fail_alloc; } if (!btrfs_super_root(disk_super)) { btrfs_err(fs_info, "invalid superblock tree root bytenr"); ret = -EINVAL; goto fail_alloc; } /* check FS state, whether FS is broken. */ if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR) WRITE_ONCE(fs_info->fs_error, -EUCLEAN); /* Set up fs_info before parsing mount options */ nodesize = btrfs_super_nodesize(disk_super); sectorsize = btrfs_super_sectorsize(disk_super); stripesize = sectorsize; fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids)); fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids)); fs_info->nodesize = nodesize; fs_info->sectorsize = sectorsize; fs_info->sectorsize_bits = ilog2(sectorsize); fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size; fs_info->stripesize = stripesize; /* * Handle the space caching options appropriately now that we have the * super block loaded and validated. */ btrfs_set_free_space_cache_settings(fs_info); if (!btrfs_check_options(fs_info, &fs_info->mount_opt, sb->s_flags)) { ret = -EINVAL; goto fail_alloc; } ret = btrfs_check_features(fs_info, !sb_rdonly(sb)); if (ret < 0) goto fail_alloc; /* * At this point our mount options are validated, if we set ->max_inline * to something non-standard make sure we truncate it to sectorsize. */ fs_info->max_inline = min_t(u64, fs_info->max_inline, fs_info->sectorsize); if (sectorsize < PAGE_SIZE) { struct btrfs_subpage_info *subpage_info; btrfs_warn(fs_info, "read-write for sector size %u with page size %lu is experimental", sectorsize, PAGE_SIZE); subpage_info = kzalloc(sizeof(*subpage_info), GFP_KERNEL); if (!subpage_info) { ret = -ENOMEM; goto fail_alloc; } btrfs_init_subpage_info(subpage_info, sectorsize); fs_info->subpage_info = subpage_info; } ret = btrfs_init_workqueues(fs_info); if (ret) goto fail_sb_buffer; sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super); sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE); /* Update the values for the current filesystem. */ sb->s_blocksize = sectorsize; sb->s_blocksize_bits = blksize_bits(sectorsize); memcpy(&sb->s_uuid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE); mutex_lock(&fs_info->chunk_mutex); ret = btrfs_read_sys_array(fs_info); mutex_unlock(&fs_info->chunk_mutex); if (ret) { btrfs_err(fs_info, "failed to read the system array: %d", ret); goto fail_sb_buffer; } generation = btrfs_super_chunk_root_generation(disk_super); level = btrfs_super_chunk_root_level(disk_super); ret = load_super_root(chunk_root, btrfs_super_chunk_root(disk_super), generation, level); if (ret) { btrfs_err(fs_info, "failed to read chunk root"); goto fail_tree_roots; } read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid, offsetof(struct btrfs_header, chunk_tree_uuid), BTRFS_UUID_SIZE); ret = btrfs_read_chunk_tree(fs_info); if (ret) { btrfs_err(fs_info, "failed to read chunk tree: %d", ret); goto fail_tree_roots; } /* * At this point we know all the devices that make this filesystem, * including the seed devices but we don't know yet if the replace * target is required. So free devices that are not part of this * filesystem but skip the replace target device which is checked * below in btrfs_init_dev_replace(). */ btrfs_free_extra_devids(fs_devices); if (!fs_devices->latest_dev->bdev) { btrfs_err(fs_info, "failed to read devices"); ret = -EIO; goto fail_tree_roots; } ret = init_tree_roots(fs_info); if (ret) goto fail_tree_roots; /* * Get zone type information of zoned block devices. This will also * handle emulation of a zoned filesystem if a regular device has the * zoned incompat feature flag set. */ ret = btrfs_get_dev_zone_info_all_devices(fs_info); if (ret) { btrfs_err(fs_info, "zoned: failed to read device zone info: %d", ret); goto fail_block_groups; } /* * If we have a uuid root and we're not being told to rescan we need to * check the generation here so we can set the * BTRFS_FS_UPDATE_UUID_TREE_GEN bit. Otherwise we could commit the * transaction during a balance or the log replay without updating the * uuid generation, and then if we crash we would rescan the uuid tree, * even though it was perfectly fine. */ if (fs_info->uuid_root && !btrfs_test_opt(fs_info, RESCAN_UUID_TREE) && fs_info->generation == btrfs_super_uuid_tree_generation(disk_super)) set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags); ret = btrfs_verify_dev_extents(fs_info); if (ret) { btrfs_err(fs_info, "failed to verify dev extents against chunks: %d", ret); goto fail_block_groups; } ret = btrfs_recover_balance(fs_info); if (ret) { btrfs_err(fs_info, "failed to recover balance: %d", ret); goto fail_block_groups; } ret = btrfs_init_dev_stats(fs_info); if (ret) { btrfs_err(fs_info, "failed to init dev_stats: %d", ret); goto fail_block_groups; } ret = btrfs_init_dev_replace(fs_info); if (ret) { btrfs_err(fs_info, "failed to init dev_replace: %d", ret); goto fail_block_groups; } ret = btrfs_check_zoned_mode(fs_info); if (ret) { btrfs_err(fs_info, "failed to initialize zoned mode: %d", ret); goto fail_block_groups; } ret = btrfs_sysfs_add_fsid(fs_devices); if (ret) { btrfs_err(fs_info, "failed to init sysfs fsid interface: %d", ret); goto fail_block_groups; } ret = btrfs_sysfs_add_mounted(fs_info); if (ret) { btrfs_err(fs_info, "failed to init sysfs interface: %d", ret); goto fail_fsdev_sysfs; } ret = btrfs_init_space_info(fs_info); if (ret) { btrfs_err(fs_info, "failed to initialize space info: %d", ret); goto fail_sysfs; } ret = btrfs_read_block_groups(fs_info); if (ret) { btrfs_err(fs_info, "failed to read block groups: %d", ret); goto fail_sysfs; } btrfs_free_zone_cache(fs_info); btrfs_check_active_zone_reservation(fs_info); if (!sb_rdonly(sb) && fs_info->fs_devices->missing_devices && !btrfs_check_rw_degradable(fs_info, NULL)) { btrfs_warn(fs_info, "writable mount is not allowed due to too many missing devices"); ret = -EINVAL; goto fail_sysfs; } fs_info->cleaner_kthread = kthread_run(cleaner_kthread, fs_info, "btrfs-cleaner"); if (IS_ERR(fs_info->cleaner_kthread)) { ret = PTR_ERR(fs_info->cleaner_kthread); goto fail_sysfs; } fs_info->transaction_kthread = kthread_run(transaction_kthread, tree_root, "btrfs-transaction"); if (IS_ERR(fs_info->transaction_kthread)) { ret = PTR_ERR(fs_info->transaction_kthread); goto fail_cleaner; } ret = btrfs_read_qgroup_config(fs_info); if (ret) goto fail_trans_kthread; if (btrfs_build_ref_tree(fs_info)) btrfs_err(fs_info, "couldn't build ref tree"); /* do not make disk changes in broken FS or nologreplay is given */ if (btrfs_super_log_root(disk_super) != 0 && !btrfs_test_opt(fs_info, NOLOGREPLAY)) { btrfs_info(fs_info, "start tree-log replay"); ret = btrfs_replay_log(fs_info, fs_devices); if (ret) goto fail_qgroup; } fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true); if (IS_ERR(fs_info->fs_root)) { ret = PTR_ERR(fs_info->fs_root); btrfs_warn(fs_info, "failed to read fs tree: %d", ret); fs_info->fs_root = NULL; goto fail_qgroup; } if (sb_rdonly(sb)) return 0; ret = btrfs_start_pre_rw_mount(fs_info); if (ret) { close_ctree(fs_info); return ret; } btrfs_discard_resume(fs_info); if (fs_info->uuid_root && (btrfs_test_opt(fs_info, RESCAN_UUID_TREE) || fs_info->generation != btrfs_super_uuid_tree_generation(disk_super))) { btrfs_info(fs_info, "checking UUID tree"); ret = btrfs_check_uuid_tree(fs_info); if (ret) { btrfs_warn(fs_info, "failed to check the UUID tree: %d", ret); close_ctree(fs_info); return ret; } } set_bit(BTRFS_FS_OPEN, &fs_info->flags); /* Kick the cleaner thread so it'll start deleting snapshots. */ if (test_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags)) wake_up_process(fs_info->cleaner_kthread); return 0; fail_qgroup: btrfs_free_qgroup_config(fs_info); fail_trans_kthread: kthread_stop(fs_info->transaction_kthread); btrfs_cleanup_transaction(fs_info); btrfs_free_fs_roots(fs_info); fail_cleaner: kthread_stop(fs_info->cleaner_kthread); /* * make sure we're done with the btree inode before we stop our * kthreads */ filemap_write_and_wait(fs_info->btree_inode->i_mapping); fail_sysfs: btrfs_sysfs_remove_mounted(fs_info); fail_fsdev_sysfs: btrfs_sysfs_remove_fsid(fs_info->fs_devices); fail_block_groups: btrfs_put_block_group_cache(fs_info); fail_tree_roots: if (fs_info->data_reloc_root) btrfs_drop_and_free_fs_root(fs_info, fs_info->data_reloc_root); free_root_pointers(fs_info, true); invalidate_inode_pages2(fs_info->btree_inode->i_mapping); fail_sb_buffer: btrfs_stop_all_workers(fs_info); btrfs_free_block_groups(fs_info); fail_alloc: btrfs_mapping_tree_free(fs_info); iput(fs_info->btree_inode); fail: btrfs_close_devices(fs_info->fs_devices); ASSERT(ret < 0); return ret; } ALLOW_ERROR_INJECTION(open_ctree, ERRNO); static void btrfs_end_super_write(struct bio *bio) { struct btrfs_device *device = bio->bi_private; struct folio_iter fi; bio_for_each_folio_all(fi, bio) { if (bio->bi_status) { btrfs_warn_rl_in_rcu(device->fs_info, "lost super block write due to IO error on %s (%d)", btrfs_dev_name(device), blk_status_to_errno(bio->bi_status)); btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_WRITE_ERRS); /* Ensure failure if the primary sb fails. */ if (bio->bi_opf & REQ_FUA) atomic_add(BTRFS_SUPER_PRIMARY_WRITE_ERROR, &device->sb_write_errors); else atomic_inc(&device->sb_write_errors); } folio_unlock(fi.folio); folio_put(fi.folio); } bio_put(bio); } struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev, int copy_num, bool drop_cache) { struct btrfs_super_block *super; struct page *page; u64 bytenr, bytenr_orig; struct address_space *mapping = bdev->bd_mapping; int ret; bytenr_orig = btrfs_sb_offset(copy_num); ret = btrfs_sb_log_location_bdev(bdev, copy_num, READ, &bytenr); if (ret == -ENOENT) return ERR_PTR(-EINVAL); else if (ret) return ERR_PTR(ret); if (bytenr + BTRFS_SUPER_INFO_SIZE >= bdev_nr_bytes(bdev)) return ERR_PTR(-EINVAL); if (drop_cache) { /* This should only be called with the primary sb. */ ASSERT(copy_num == 0); /* * Drop the page of the primary superblock, so later read will * always read from the device. */ invalidate_inode_pages2_range(mapping, bytenr >> PAGE_SHIFT, (bytenr + BTRFS_SUPER_INFO_SIZE) >> PAGE_SHIFT); } page = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS); if (IS_ERR(page)) return ERR_CAST(page); super = page_address(page); if (btrfs_super_magic(super) != BTRFS_MAGIC) { btrfs_release_disk_super(super); return ERR_PTR(-ENODATA); } if (btrfs_super_bytenr(super) != bytenr_orig) { btrfs_release_disk_super(super); return ERR_PTR(-EINVAL); } return super; } struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev) { struct btrfs_super_block *super, *latest = NULL; int i; u64 transid = 0; /* we would like to check all the supers, but that would make * a btrfs mount succeed after a mkfs from a different FS. * So, we need to add a special mount option to scan for * later supers, using BTRFS_SUPER_MIRROR_MAX instead */ for (i = 0; i < 1; i++) { super = btrfs_read_dev_one_super(bdev, i, false); if (IS_ERR(super)) continue; if (!latest || btrfs_super_generation(super) > transid) { if (latest) btrfs_release_disk_super(super); latest = super; transid = btrfs_super_generation(super); } } return super; } /* * Write superblock @sb to the @device. Do not wait for completion, all the * folios we use for writing are locked. * * Write @max_mirrors copies of the superblock, where 0 means default that fit * the expected device size at commit time. Note that max_mirrors must be * same for write and wait phases. * * Return number of errors when folio is not found or submission fails. */ static int write_dev_supers(struct btrfs_device *device, struct btrfs_super_block *sb, int max_mirrors) { struct btrfs_fs_info *fs_info = device->fs_info; struct address_space *mapping = device->bdev->bd_mapping; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); int i; int ret; u64 bytenr, bytenr_orig; atomic_set(&device->sb_write_errors, 0); if (max_mirrors == 0) max_mirrors = BTRFS_SUPER_MIRROR_MAX; shash->tfm = fs_info->csum_shash; for (i = 0; i < max_mirrors; i++) { struct folio *folio; struct bio *bio; struct btrfs_super_block *disk_super; size_t offset; bytenr_orig = btrfs_sb_offset(i); ret = btrfs_sb_log_location(device, i, WRITE, &bytenr); if (ret == -ENOENT) { continue; } else if (ret < 0) { btrfs_err(device->fs_info, "couldn't get super block location for mirror %d", i); atomic_inc(&device->sb_write_errors); continue; } if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->commit_total_bytes) break; btrfs_set_super_bytenr(sb, bytenr_orig); crypto_shash_digest(shash, (const char *)sb + BTRFS_CSUM_SIZE, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, sb->csum); folio = __filemap_get_folio(mapping, bytenr >> PAGE_SHIFT, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); if (IS_ERR(folio)) { btrfs_err(device->fs_info, "couldn't get super block page for bytenr %llu", bytenr); atomic_inc(&device->sb_write_errors); continue; } ASSERT(folio_order(folio) == 0); offset = offset_in_folio(folio, bytenr); disk_super = folio_address(folio) + offset; memcpy(disk_super, sb, BTRFS_SUPER_INFO_SIZE); /* * Directly use bios here instead of relying on the page cache * to do I/O, so we don't lose the ability to do integrity * checking. */ bio = bio_alloc(device->bdev, 1, REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, GFP_NOFS); bio->bi_iter.bi_sector = bytenr >> SECTOR_SHIFT; bio->bi_private = device; bio->bi_end_io = btrfs_end_super_write; bio_add_folio_nofail(bio, folio, BTRFS_SUPER_INFO_SIZE, offset); /* * We FUA only the first super block. The others we allow to * go down lazy and there's a short window where the on-disk * copies might still contain the older version. */ if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER)) bio->bi_opf |= REQ_FUA; submit_bio(bio); if (btrfs_advance_sb_log(device, i)) atomic_inc(&device->sb_write_errors); } return atomic_read(&device->sb_write_errors) < i ? 0 : -1; } /* * Wait for write completion of superblocks done by write_dev_supers, * @max_mirrors same for write and wait phases. * * Return -1 if primary super block write failed or when there were no super block * copies written. Otherwise 0. */ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors) { int i; int errors = 0; bool primary_failed = false; int ret; u64 bytenr; if (max_mirrors == 0) max_mirrors = BTRFS_SUPER_MIRROR_MAX; for (i = 0; i < max_mirrors; i++) { struct folio *folio; ret = btrfs_sb_log_location(device, i, READ, &bytenr); if (ret == -ENOENT) { break; } else if (ret < 0) { errors++; if (i == 0) primary_failed = true; continue; } if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->commit_total_bytes) break; folio = filemap_get_folio(device->bdev->bd_mapping, bytenr >> PAGE_SHIFT); /* If the folio has been removed, then we know it completed. */ if (IS_ERR(folio)) continue; ASSERT(folio_order(folio) == 0); /* Folio will be unlocked once the write completes. */ folio_wait_locked(folio); folio_put(folio); } errors += atomic_read(&device->sb_write_errors); if (errors >= BTRFS_SUPER_PRIMARY_WRITE_ERROR) primary_failed = true; if (primary_failed) { btrfs_err(device->fs_info, "error writing primary super block to device %llu", device->devid); return -1; } return errors < i ? 0 : -1; } /* * endio for the write_dev_flush, this will wake anyone waiting * for the barrier when it is done */ static void btrfs_end_empty_barrier(struct bio *bio) { bio_uninit(bio); complete(bio->bi_private); } /* * Submit a flush request to the device if it supports it. Error handling is * done in the waiting counterpart. */ static void write_dev_flush(struct btrfs_device *device) { struct bio *bio = &device->flush_bio; device->last_flush_error = BLK_STS_OK; bio_init(bio, device->bdev, NULL, 0, REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH); bio->bi_end_io = btrfs_end_empty_barrier; init_completion(&device->flush_wait); bio->bi_private = &device->flush_wait; submit_bio(bio); set_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state); } /* * If the flush bio has been submitted by write_dev_flush, wait for it. * Return true for any error, and false otherwise. */ static bool wait_dev_flush(struct btrfs_device *device) { struct bio *bio = &device->flush_bio; if (!test_and_clear_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state)) return false; wait_for_completion_io(&device->flush_wait); if (bio->bi_status) { device->last_flush_error = bio->bi_status; btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_FLUSH_ERRS); return true; } return false; } /* * send an empty flush down to each device in parallel, * then wait for them */ static int barrier_all_devices(struct btrfs_fs_info *info) { struct list_head *head; struct btrfs_device *dev; int errors_wait = 0; lockdep_assert_held(&info->fs_devices->device_list_mutex); /* send down all the barriers */ head = &info->fs_devices->devices; list_for_each_entry(dev, head, dev_list) { if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) continue; if (!dev->bdev) continue; if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue; write_dev_flush(dev); } /* wait for all the barriers */ list_for_each_entry(dev, head, dev_list) { if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) continue; if (!dev->bdev) { errors_wait++; continue; } if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue; if (wait_dev_flush(dev)) errors_wait++; } /* * Checks last_flush_error of disks in order to determine the device * state. */ if (errors_wait && !btrfs_check_rw_degradable(info, NULL)) return -EIO; return 0; } int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags) { int raid_type; int min_tolerated = INT_MAX; if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 || (flags & BTRFS_AVAIL_ALLOC_BIT_SINGLE)) min_tolerated = min_t(int, min_tolerated, btrfs_raid_array[BTRFS_RAID_SINGLE]. tolerated_failures); for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) { if (raid_type == BTRFS_RAID_SINGLE) continue; if (!(flags & btrfs_raid_array[raid_type].bg_flag)) continue; min_tolerated = min_t(int, min_tolerated, btrfs_raid_array[raid_type]. tolerated_failures); } if (min_tolerated == INT_MAX) { pr_warn("BTRFS: unknown raid flag: %llu", flags); min_tolerated = 0; } return min_tolerated; } int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) { struct list_head *head; struct btrfs_device *dev; struct btrfs_super_block *sb; struct btrfs_dev_item *dev_item; int ret; int do_barriers; int max_errors; int total_errors = 0; u64 flags; do_barriers = !btrfs_test_opt(fs_info, NOBARRIER); /* * max_mirrors == 0 indicates we're from commit_transaction, * not from fsync where the tree roots in fs_info have not * been consistent on disk. */ if (max_mirrors == 0) backup_super_roots(fs_info); sb = fs_info->super_for_commit; dev_item = &sb->dev_item; mutex_lock(&fs_info->fs_devices->device_list_mutex); head = &fs_info->fs_devices->devices; max_errors = btrfs_super_num_devices(fs_info->super_copy) - 1; if (do_barriers) { ret = barrier_all_devices(fs_info); if (ret) { mutex_unlock( &fs_info->fs_devices->device_list_mutex); btrfs_handle_fs_error(fs_info, ret, "errors while submitting device barriers."); return ret; } } list_for_each_entry(dev, head, dev_list) { if (!dev->bdev) { total_errors++; continue; } if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue; btrfs_set_stack_device_generation(dev_item, 0); btrfs_set_stack_device_type(dev_item, dev->type); btrfs_set_stack_device_id(dev_item, dev->devid); btrfs_set_stack_device_total_bytes(dev_item, dev->commit_total_bytes); btrfs_set_stack_device_bytes_used(dev_item, dev->commit_bytes_used); btrfs_set_stack_device_io_align(dev_item, dev->io_align); btrfs_set_stack_device_io_width(dev_item, dev->io_width); btrfs_set_stack_device_sector_size(dev_item, dev->sector_size); memcpy(dev_item->uuid, dev->uuid, BTRFS_UUID_SIZE); memcpy(dev_item->fsid, dev->fs_devices->metadata_uuid, BTRFS_FSID_SIZE); flags = btrfs_super_flags(sb); btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN); ret = btrfs_validate_write_super(fs_info, sb); if (ret < 0) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); btrfs_handle_fs_error(fs_info, -EUCLEAN, "unexpected superblock corruption detected"); return -EUCLEAN; } ret = write_dev_supers(dev, sb, max_mirrors); if (ret) total_errors++; } if (total_errors > max_errors) { btrfs_err(fs_info, "%d errors while writing supers", total_errors); mutex_unlock(&fs_info->fs_devices->device_list_mutex); /* FUA is masked off if unsupported and can't be the reason */ btrfs_handle_fs_error(fs_info, -EIO, "%d errors while writing supers", total_errors); return -EIO; } total_errors = 0; list_for_each_entry(dev, head, dev_list) { if (!dev->bdev) continue; if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue; ret = wait_dev_supers(dev, max_mirrors); if (ret) total_errors++; } mutex_unlock(&fs_info->fs_devices->device_list_mutex); if (total_errors > max_errors) { btrfs_handle_fs_error(fs_info, -EIO, "%d errors while writing supers", total_errors); return -EIO; } return 0; } /* Drop a fs root from the radix tree and free it. */ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) { bool drop_ref = false; spin_lock(&fs_info->fs_roots_radix_lock); radix_tree_delete(&fs_info->fs_roots_radix, (unsigned long)btrfs_root_id(root)); if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state)) drop_ref = true; spin_unlock(&fs_info->fs_roots_radix_lock); if (BTRFS_FS_ERROR(fs_info)) { ASSERT(root->log_root == NULL); if (root->reloc_root) { btrfs_put_root(root->reloc_root); root->reloc_root = NULL; } } if (drop_ref) btrfs_put_root(root); } int btrfs_commit_super(struct btrfs_fs_info *fs_info) { mutex_lock(&fs_info->cleaner_mutex); btrfs_run_delayed_iputs(fs_info); mutex_unlock(&fs_info->cleaner_mutex); wake_up_process(fs_info->cleaner_kthread); /* wait until ongoing cleanup work done */ down_write(&fs_info->cleanup_work_sem); up_write(&fs_info->cleanup_work_sem); return btrfs_commit_current_transaction(fs_info->tree_root); } static void warn_about_uncommitted_trans(struct btrfs_fs_info *fs_info) { struct btrfs_transaction *trans; struct btrfs_transaction *tmp; bool found = false; /* * This function is only called at the very end of close_ctree(), * thus no other running transaction, no need to take trans_lock. */ ASSERT(test_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags)); list_for_each_entry_safe(trans, tmp, &fs_info->trans_list, list) { struct extent_state *cached = NULL; u64 dirty_bytes = 0; u64 cur = 0; u64 found_start; u64 found_end; found = true; while (find_first_extent_bit(&trans->dirty_pages, cur, &found_start, &found_end, EXTENT_DIRTY, &cached)) { dirty_bytes += found_end + 1 - found_start; cur = found_end + 1; } btrfs_warn(fs_info, "transaction %llu (with %llu dirty metadata bytes) is not committed", trans->transid, dirty_bytes); btrfs_cleanup_one_transaction(trans, fs_info); if (trans == fs_info->running_transaction) fs_info->running_transaction = NULL; list_del_init(&trans->list); btrfs_put_transaction(trans); trace_btrfs_transaction_commit(fs_info); } ASSERT(!found); } void __cold close_ctree(struct btrfs_fs_info *fs_info) { int ret; set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); /* * If we had UNFINISHED_DROPS we could still be processing them, so * clear that bit and wake up relocation so it can stop. * We must do this before stopping the block group reclaim task, because * at btrfs_relocate_block_group() we wait for this bit, and after the * wait we stop with -EINTR if btrfs_fs_closing() returns non-zero - we * have just set BTRFS_FS_CLOSING_START, so btrfs_fs_closing() will * return 1. */ btrfs_wake_unfinished_drop(fs_info); /* * We may have the reclaim task running and relocating a data block group, * in which case it may create delayed iputs. So stop it before we park * the cleaner kthread otherwise we can get new delayed iputs after * parking the cleaner, and that can make the async reclaim task to hang * if it's waiting for delayed iputs to complete, since the cleaner is * parked and can not run delayed iputs - this will make us hang when * trying to stop the async reclaim task. */ cancel_work_sync(&fs_info->reclaim_bgs_work); /* * We don't want the cleaner to start new transactions, add more delayed * iputs, etc. while we're closing. We can't use kthread_stop() yet * because that frees the task_struct, and the transaction kthread might * still try to wake up the cleaner. */ kthread_park(fs_info->cleaner_kthread); /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); /* wait for the uuid_scan task to finish */ down(&fs_info->uuid_tree_rescan_sem); /* avoid complains from lockdep et al., set sem back to initial state */ up(&fs_info->uuid_tree_rescan_sem); /* pause restriper - we want to resume on mount */ btrfs_pause_balance(fs_info); btrfs_dev_replace_suspend_for_unmount(fs_info); btrfs_scrub_cancel(fs_info); /* wait for any defraggers to finish */ wait_event(fs_info->transaction_wait, (atomic_read(&fs_info->defrag_running) == 0)); /* clear out the rbtree of defraggable inodes */ btrfs_cleanup_defrag_inodes(fs_info); /* * After we parked the cleaner kthread, ordered extents may have * completed and created new delayed iputs. If one of the async reclaim * tasks is running and in the RUN_DELAYED_IPUTS flush state, then we * can hang forever trying to stop it, because if a delayed iput is * added after it ran btrfs_run_delayed_iputs() and before it called * btrfs_wait_on_delayed_iputs(), it will hang forever since there is * no one else to run iputs. * * So wait for all ongoing ordered extents to complete and then run * delayed iputs. This works because once we reach this point no one * can either create new ordered extents nor create delayed iputs * through some other means. * * Also note that btrfs_wait_ordered_roots() is not safe here, because * it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent, * but the delayed iput for the respective inode is made only when doing * the final btrfs_put_ordered_extent() (which must happen at * btrfs_finish_ordered_io() when we are unmounting). */ btrfs_flush_workqueue(fs_info->endio_write_workers); /* Ordered extents for free space inodes. */ btrfs_flush_workqueue(fs_info->endio_freespace_worker); btrfs_run_delayed_iputs(fs_info); cancel_work_sync(&fs_info->async_reclaim_work); cancel_work_sync(&fs_info->async_data_reclaim_work); cancel_work_sync(&fs_info->preempt_reclaim_work); /* Cancel or finish ongoing discard work */ btrfs_discard_cleanup(fs_info); if (!sb_rdonly(fs_info->sb)) { /* * The cleaner kthread is stopped, so do one final pass over * unused block groups. */ btrfs_delete_unused_bgs(fs_info); /* * There might be existing delayed inode workers still running * and holding an empty delayed inode item. We must wait for * them to complete first because they can create a transaction. * This happens when someone calls btrfs_balance_delayed_items() * and then a transaction commit runs the same delayed nodes * before any delayed worker has done something with the nodes. * We must wait for any worker here and not at transaction * commit time since that could cause a deadlock. * This is a very rare case. */ btrfs_flush_workqueue(fs_info->delayed_workers); ret = btrfs_commit_super(fs_info); if (ret) btrfs_err(fs_info, "commit super ret %d", ret); } if (BTRFS_FS_ERROR(fs_info)) btrfs_error_commit_super(fs_info); kthread_stop(fs_info->transaction_kthread); kthread_stop(fs_info->cleaner_kthread); ASSERT(list_empty(&fs_info->delayed_iputs)); set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags); if (btrfs_check_quota_leak(fs_info)) { WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); btrfs_err(fs_info, "qgroup reserved space leaked"); } btrfs_free_qgroup_config(fs_info); ASSERT(list_empty(&fs_info->delalloc_roots)); if (percpu_counter_sum(&fs_info->delalloc_bytes)) { btrfs_info(fs_info, "at unmount delalloc count %lld", percpu_counter_sum(&fs_info->delalloc_bytes)); } if (percpu_counter_sum(&fs_info->ordered_bytes)) btrfs_info(fs_info, "at unmount dio bytes count %lld", percpu_counter_sum(&fs_info->ordered_bytes)); btrfs_sysfs_remove_mounted(fs_info); btrfs_sysfs_remove_fsid(fs_info->fs_devices); btrfs_put_block_group_cache(fs_info); /* * we must make sure there is not any read request to * submit after we stopping all workers. */ invalidate_inode_pages2(fs_info->btree_inode->i_mapping); btrfs_stop_all_workers(fs_info); /* We shouldn't have any transaction open at this point */ warn_about_uncommitted_trans(fs_info); clear_bit(BTRFS_FS_OPEN, &fs_info->flags); free_root_pointers(fs_info, true); btrfs_free_fs_roots(fs_info); /* * We must free the block groups after dropping the fs_roots as we could * have had an IO error and have left over tree log blocks that aren't * cleaned up until the fs roots are freed. This makes the block group * accounting appear to be wrong because there's pending reserved bytes, * so make sure we do the block group cleanup afterwards. */ btrfs_free_block_groups(fs_info); iput(fs_info->btree_inode); btrfs_mapping_tree_free(fs_info); btrfs_close_devices(fs_info->fs_devices); } void btrfs_mark_buffer_dirty(struct btrfs_trans_handle *trans, struct extent_buffer *buf) { struct btrfs_fs_info *fs_info = buf->fs_info; u64 transid = btrfs_header_generation(buf); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS /* * This is a fast path so only do this check if we have sanity tests * enabled. Normal people shouldn't be using unmapped buffers as dirty * outside of the sanity tests. */ if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags))) return; #endif /* This is an active transaction (its state < TRANS_STATE_UNBLOCKED). */ ASSERT(trans->transid == fs_info->generation); btrfs_assert_tree_write_locked(buf); if (unlikely(transid != fs_info->generation)) { btrfs_abort_transaction(trans, -EUCLEAN); btrfs_crit(fs_info, "dirty buffer transid mismatch, logical %llu found transid %llu running transid %llu", buf->start, transid, fs_info->generation); } set_extent_buffer_dirty(buf); } static void __btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info, int flush_delayed) { /* * looks as though older kernels can get into trouble with * this code, they end up stuck in balance_dirty_pages forever */ int ret; if (current->flags & PF_MEMALLOC) return; if (flush_delayed) btrfs_balance_delayed_items(fs_info); ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes, BTRFS_DIRTY_METADATA_THRESH, fs_info->dirty_metadata_batch); if (ret > 0) { balance_dirty_pages_ratelimited(fs_info->btree_inode->i_mapping); } } void btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info) { __btrfs_btree_balance_dirty(fs_info, 1); } void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info) { __btrfs_btree_balance_dirty(fs_info, 0); } static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) { /* cleanup FS via transaction */ btrfs_cleanup_transaction(fs_info); mutex_lock(&fs_info->cleaner_mutex); btrfs_run_delayed_iputs(fs_info); mutex_unlock(&fs_info->cleaner_mutex); down_write(&fs_info->cleanup_work_sem); up_write(&fs_info->cleanup_work_sem); } static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info) { struct btrfs_root *gang[8]; u64 root_objectid = 0; int ret; spin_lock(&fs_info->fs_roots_radix_lock); while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, (void **)gang, root_objectid, ARRAY_SIZE(gang))) != 0) { int i; for (i = 0; i < ret; i++) gang[i] = btrfs_grab_root(gang[i]); spin_unlock(&fs_info->fs_roots_radix_lock); for (i = 0; i < ret; i++) { if (!gang[i]) continue; root_objectid = btrfs_root_id(gang[i]); btrfs_free_log(NULL, gang[i]); btrfs_put_root(gang[i]); } root_objectid++; spin_lock(&fs_info->fs_roots_radix_lock); } spin_unlock(&fs_info->fs_roots_radix_lock); btrfs_free_log_root_tree(NULL, fs_info); } static void btrfs_destroy_ordered_extents(struct btrfs_root *root) { struct btrfs_ordered_extent *ordered; spin_lock(&root->ordered_extent_lock); /* * This will just short circuit the ordered completion stuff which will * make sure the ordered extent gets properly cleaned up. */ list_for_each_entry(ordered, &root->ordered_extents, root_extent_list) set_bit(BTRFS_ORDERED_IOERR, &ordered->flags); spin_unlock(&root->ordered_extent_lock); } static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; LIST_HEAD(splice); spin_lock(&fs_info->ordered_root_lock); list_splice_init(&fs_info->ordered_roots, &splice); while (!list_empty(&splice)) { root = list_first_entry(&splice, struct btrfs_root, ordered_root); list_move_tail(&root->ordered_root, &fs_info->ordered_roots); spin_unlock(&fs_info->ordered_root_lock); btrfs_destroy_ordered_extents(root); cond_resched(); spin_lock(&fs_info->ordered_root_lock); } spin_unlock(&fs_info->ordered_root_lock); /* * We need this here because if we've been flipped read-only we won't * get sync() from the umount, so we need to make sure any ordered * extents that haven't had their dirty pages IO start writeout yet * actually get run and error out properly. */ btrfs_wait_ordered_roots(fs_info, U64_MAX, NULL); } static void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info) { struct rb_node *node; struct btrfs_delayed_ref_root *delayed_refs = &trans->delayed_refs; struct btrfs_delayed_ref_node *ref; spin_lock(&delayed_refs->lock); while ((node = rb_first_cached(&delayed_refs->href_root)) != NULL) { struct btrfs_delayed_ref_head *head; struct rb_node *n; bool pin_bytes = false; head = rb_entry(node, struct btrfs_delayed_ref_head, href_node); if (btrfs_delayed_ref_lock(delayed_refs, head)) continue; spin_lock(&head->lock); while ((n = rb_first_cached(&head->ref_tree)) != NULL) { ref = rb_entry(n, struct btrfs_delayed_ref_node, ref_node); rb_erase_cached(&ref->ref_node, &head->ref_tree); RB_CLEAR_NODE(&ref->ref_node); if (!list_empty(&ref->add_list)) list_del(&ref->add_list); atomic_dec(&delayed_refs->num_entries); btrfs_put_delayed_ref(ref); btrfs_delayed_refs_rsv_release(fs_info, 1, 0); } if (head->must_insert_reserved) pin_bytes = true; btrfs_free_delayed_extent_op(head->extent_op); btrfs_delete_ref_head(delayed_refs, head); spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); mutex_unlock(&head->mutex); if (pin_bytes) { struct btrfs_block_group *cache; cache = btrfs_lookup_block_group(fs_info, head->bytenr); BUG_ON(!cache); spin_lock(&cache->space_info->lock); spin_lock(&cache->lock); cache->pinned += head->num_bytes; btrfs_space_info_update_bytes_pinned(fs_info, cache->space_info, head->num_bytes); cache->reserved -= head->num_bytes; cache->space_info->bytes_reserved -= head->num_bytes; spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); btrfs_put_block_group(cache); btrfs_error_unpin_extent_range(fs_info, head->bytenr, head->bytenr + head->num_bytes - 1); } btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); btrfs_put_delayed_ref_head(head); cond_resched(); spin_lock(&delayed_refs->lock); } btrfs_qgroup_destroy_extent_records(trans); spin_unlock(&delayed_refs->lock); } static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) { struct btrfs_inode *btrfs_inode; LIST_HEAD(splice); spin_lock(&root->delalloc_lock); list_splice_init(&root->delalloc_inodes, &splice); while (!list_empty(&splice)) { struct inode *inode = NULL; btrfs_inode = list_first_entry(&splice, struct btrfs_inode, delalloc_inodes); btrfs_del_delalloc_inode(btrfs_inode); spin_unlock(&root->delalloc_lock); /* * Make sure we get a live inode and that it'll not disappear * meanwhile. */ inode = igrab(&btrfs_inode->vfs_inode); if (inode) { unsigned int nofs_flag; nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); memalloc_nofs_restore(nofs_flag); iput(inode); } spin_lock(&root->delalloc_lock); } spin_unlock(&root->delalloc_lock); } static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; LIST_HEAD(splice); spin_lock(&fs_info->delalloc_root_lock); list_splice_init(&fs_info->delalloc_roots, &splice); while (!list_empty(&splice)) { root = list_first_entry(&splice, struct btrfs_root, delalloc_root); root = btrfs_grab_root(root); BUG_ON(!root); spin_unlock(&fs_info->delalloc_root_lock); btrfs_destroy_delalloc_inodes(root); btrfs_put_root(root); spin_lock(&fs_info->delalloc_root_lock); } spin_unlock(&fs_info->delalloc_root_lock); } static void btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info, struct extent_io_tree *dirty_pages, int mark) { struct extent_buffer *eb; u64 start = 0; u64 end; while (find_first_extent_bit(dirty_pages, start, &start, &end, mark, NULL)) { clear_extent_bits(dirty_pages, start, end, mark); while (start <= end) { eb = find_extent_buffer(fs_info, start); start += fs_info->nodesize; if (!eb) continue; btrfs_tree_lock(eb); wait_on_extent_buffer_writeback(eb); btrfs_clear_buffer_dirty(NULL, eb); btrfs_tree_unlock(eb); free_extent_buffer_stale(eb); } } } static void btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, struct extent_io_tree *unpin) { u64 start; u64 end; while (1) { struct extent_state *cached_state = NULL; /* * The btrfs_finish_extent_commit() may get the same range as * ours between find_first_extent_bit and clear_extent_dirty. * Hence, hold the unused_bg_unpin_mutex to avoid double unpin * the same extent range. */ mutex_lock(&fs_info->unused_bg_unpin_mutex); if (!find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY, &cached_state)) { mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; } clear_extent_dirty(unpin, start, end, &cached_state); free_extent_state(cached_state); btrfs_error_unpin_extent_range(fs_info, start, end); mutex_unlock(&fs_info->unused_bg_unpin_mutex); cond_resched(); } } static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) { struct inode *inode; inode = cache->io_ctl.inode; if (inode) { unsigned int nofs_flag; nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); memalloc_nofs_restore(nofs_flag); BTRFS_I(inode)->generation = 0; cache->io_ctl.inode = NULL; iput(inode); } ASSERT(cache->io_ctl.pages == NULL); btrfs_put_block_group(cache); } void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, struct btrfs_fs_info *fs_info) { struct btrfs_block_group *cache; spin_lock(&cur_trans->dirty_bgs_lock); while (!list_empty(&cur_trans->dirty_bgs)) { cache = list_first_entry(&cur_trans->dirty_bgs, struct btrfs_block_group, dirty_list); if (!list_empty(&cache->io_list)) { spin_unlock(&cur_trans->dirty_bgs_lock); list_del_init(&cache->io_list); btrfs_cleanup_bg_io(cache); spin_lock(&cur_trans->dirty_bgs_lock); } list_del_init(&cache->dirty_list); spin_lock(&cache->lock); cache->disk_cache_state = BTRFS_DC_ERROR; spin_unlock(&cache->lock); spin_unlock(&cur_trans->dirty_bgs_lock); btrfs_put_block_group(cache); btrfs_dec_delayed_refs_rsv_bg_updates(fs_info); spin_lock(&cur_trans->dirty_bgs_lock); } spin_unlock(&cur_trans->dirty_bgs_lock); /* * Refer to the definition of io_bgs member for details why it's safe * to use it without any locking */ while (!list_empty(&cur_trans->io_bgs)) { cache = list_first_entry(&cur_trans->io_bgs, struct btrfs_block_group, io_list); list_del_init(&cache->io_list); spin_lock(&cache->lock); cache->disk_cache_state = BTRFS_DC_ERROR; spin_unlock(&cache->lock); btrfs_cleanup_bg_io(cache); } } static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info) { struct btrfs_root *gang[8]; int i; int ret; spin_lock(&fs_info->fs_roots_radix_lock); while (1) { ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix, (void **)gang, 0, ARRAY_SIZE(gang), BTRFS_ROOT_TRANS_TAG); if (ret == 0) break; for (i = 0; i < ret; i++) { struct btrfs_root *root = gang[i]; btrfs_qgroup_free_meta_all_pertrans(root); radix_tree_tag_clear(&fs_info->fs_roots_radix, (unsigned long)btrfs_root_id(root), BTRFS_ROOT_TRANS_TAG); } } spin_unlock(&fs_info->fs_roots_radix_lock); } void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_fs_info *fs_info) { struct btrfs_device *dev, *tmp; btrfs_cleanup_dirty_bgs(cur_trans, fs_info); ASSERT(list_empty(&cur_trans->dirty_bgs)); ASSERT(list_empty(&cur_trans->io_bgs)); list_for_each_entry_safe(dev, tmp, &cur_trans->dev_update_list, post_commit_list) { list_del_init(&dev->post_commit_list); } btrfs_destroy_delayed_refs(cur_trans, fs_info); cur_trans->state = TRANS_STATE_COMMIT_START; wake_up(&fs_info->transaction_blocked_wait); cur_trans->state = TRANS_STATE_UNBLOCKED; wake_up(&fs_info->transaction_wait); btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages, EXTENT_DIRTY); btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); } static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) { struct btrfs_transaction *t; mutex_lock(&fs_info->transaction_kthread_mutex); spin_lock(&fs_info->trans_lock); while (!list_empty(&fs_info->trans_list)) { t = list_first_entry(&fs_info->trans_list, struct btrfs_transaction, list); if (t->state >= TRANS_STATE_COMMIT_PREP) { refcount_inc(&t->use_count); spin_unlock(&fs_info->trans_lock); btrfs_wait_for_commit(fs_info, t->transid); btrfs_put_transaction(t); spin_lock(&fs_info->trans_lock); continue; } if (t == fs_info->running_transaction) { t->state = TRANS_STATE_COMMIT_DOING; spin_unlock(&fs_info->trans_lock); /* * We wait for 0 num_writers since we don't hold a trans * handle open currently for this transaction. */ wait_event(t->writer_wait, atomic_read(&t->num_writers) == 0); } else { spin_unlock(&fs_info->trans_lock); } btrfs_cleanup_one_transaction(t, fs_info); spin_lock(&fs_info->trans_lock); if (t == fs_info->running_transaction) fs_info->running_transaction = NULL; list_del_init(&t->list); spin_unlock(&fs_info->trans_lock); btrfs_put_transaction(t); trace_btrfs_transaction_commit(fs_info); spin_lock(&fs_info->trans_lock); } spin_unlock(&fs_info->trans_lock); btrfs_destroy_all_ordered_extents(fs_info); btrfs_destroy_delayed_inodes(fs_info); btrfs_assert_delayed_root_empty(fs_info); btrfs_destroy_all_delalloc_inodes(fs_info); btrfs_drop_all_logs(fs_info); btrfs_free_all_qgroup_pertrans(fs_info); mutex_unlock(&fs_info->transaction_kthread_mutex); return 0; } int btrfs_init_root_free_objectid(struct btrfs_root *root) { struct btrfs_path *path; int ret; struct extent_buffer *l; struct btrfs_key search_key; struct btrfs_key found_key; int slot; path = btrfs_alloc_path(); if (!path) return -ENOMEM; search_key.objectid = BTRFS_LAST_FREE_OBJECTID; search_key.type = -1; search_key.offset = (u64)-1; ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) goto error; if (ret == 0) { /* * Key with offset -1 found, there would have to exist a root * with such id, but this is out of valid range. */ ret = -EUCLEAN; goto error; } if (path->slots[0] > 0) { slot = path->slots[0] - 1; l = path->nodes[0]; btrfs_item_key_to_cpu(l, &found_key, slot); root->free_objectid = max_t(u64, found_key.objectid + 1, BTRFS_FIRST_FREE_OBJECTID); } else { root->free_objectid = BTRFS_FIRST_FREE_OBJECTID; } ret = 0; error: btrfs_free_path(path); return ret; } int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid) { int ret; mutex_lock(&root->objectid_mutex); if (unlikely(root->free_objectid >= BTRFS_LAST_FREE_OBJECTID)) { btrfs_warn(root->fs_info, "the objectid of root %llu reaches its highest value", btrfs_root_id(root)); ret = -ENOSPC; goto out; } *objectid = root->free_objectid++; ret = 0; out: mutex_unlock(&root->objectid_mutex); return ret; } |
| 4 4 4 1 1 4 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 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 | // 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. * * PACKET - implements raw packet sockets. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Fixes: * Alan Cox : verify_area() now used correctly * Alan Cox : new skbuff lists, look ma no backlogs! * Alan Cox : tidied skbuff lists. * Alan Cox : Now uses generic datagram routines I * added. Also fixed the peek/read crash * from all old Linux datagram code. * Alan Cox : Uses the improved datagram code. * Alan Cox : Added NULL's for socket options. * Alan Cox : Re-commented the code. * Alan Cox : Use new kernel side addressing * Rob Janssen : Correct MTU usage. * Dave Platt : Counter leaks caused by incorrect * interrupt locking and some slightly * dubious gcc output. Can you read * compiler: it said _VOLATILE_ * Richard Kooijman : Timestamp fixes. * Alan Cox : New buffers. Use sk->mac.raw. * Alan Cox : sendmsg/recvmsg support. * Alan Cox : Protocol setting support * Alexey Kuznetsov : Untied from IPv4 stack. * Cyrus Durgin : Fixed kerneld for kmod. * Michal Ostrowski : Module initialization cleanup. * Ulises Alonso : Frame number limit removal and * packet_set_ring memory leak. * Eric Biederman : Allow for > 8 byte hardware addresses. * The convention is that longer addresses * will simply extend the hardware address * byte arrays at the end of sockaddr_ll * and packet_mreq. * Johann Baudy : Added TX RING. * Chetan Loke : Implemented TPACKET_V3 block abstraction * layer. * Copyright (C) 2011, <lokec@ccs.neu.edu> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/wireless.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/io.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/module.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/if_vlan.h> #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> #include <linux/percpu.h> #ifdef CONFIG_INET #include <net/inet_common.h> #endif #include <linux/bpf.h> #include <net/compat.h> #include <linux/netfilter_netdev.h> #include "internal.h" /* Assumptions: - If the device has no dev->header_ops->create, there is no LL header visible above the device. In this case, its hard_header_len should be 0. The device may prepend its own header internally. In this case, its needed_headroom should be set to the space needed for it to add its internal header. For example, a WiFi driver pretending to be an Ethernet driver should set its hard_header_len to be the Ethernet header length, and set its needed_headroom to be (the real WiFi header length - the fake Ethernet header length). - packet socket receives packets with pulled ll header, so that SOCK_RAW should push it back. On receive: ----------- Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header Incoming, dev_has_header(dev) == false mac_header -> data However drivers often make it point to the ll header. This is incorrect because the ll header should be invisible to us. data -> data Outgoing, dev_has_header(dev) == false mac_header -> data. ll header is invisible to us. data -> data Resume If dev_has_header(dev) == false we are unable to restore the ll header, because it is invisible to us. On transmit: ------------ dev_has_header(dev) == true mac_header -> ll header data -> ll header dev_has_header(dev) == false (ll header is invisible to us) mac_header -> data data -> data We should set network_header on output to the correct position, packet classifier depends on it. */ /* Private packet socket structures. */ /* identical to struct packet_mreq except it has * a longer address field. */ struct packet_mreq_max { int mr_ifindex; unsigned short mr_type; unsigned short mr_alen; unsigned char mr_address[MAX_ADDR_LEN]; }; union tpacket_uhdr { struct tpacket_hdr *h1; struct tpacket2_hdr *h2; struct tpacket3_hdr *h3; void *raw; }; static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring); #define V3_ALIGNMENT (8) #define BLK_HDR_LEN (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT)) #define BLK_PLUS_PRIV(sz_of_priv) \ (BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT)) #define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status) #define BLOCK_NUM_PKTS(x) ((x)->hdr.bh1.num_pkts) #define BLOCK_O2FP(x) ((x)->hdr.bh1.offset_to_first_pkt) #define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) #define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) #define BLOCK_O2PRIV(x) ((x)->offset_to_priv) struct packet_sock; static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status); static void packet_increment_head(struct packet_ring_buffer *buff); static int prb_curr_blk_in_use(struct tpacket_block_desc *); static void *prb_dispatch_next_block(struct tpacket_kbdq_core *, struct packet_sock *); static void prb_retire_current_block(struct tpacket_kbdq_core *, struct packet_sock *, unsigned int status); static int prb_queue_frozen(struct tpacket_kbdq_core *); static void prb_open_block(struct tpacket_kbdq_core *, struct tpacket_block_desc *); static void prb_retire_rx_blk_timer_expired(struct timer_list *); static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *); static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_clear_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); static u16 packet_pick_tx_queue(struct sk_buff *skb); struct packet_skb_cb { union { struct sockaddr_pkt pkt; union { /* Trick: alias skb original length with * ll.sll_family and ll.protocol in order * to save room. */ unsigned int origlen; struct sockaddr_ll ll; }; } sa; }; #define vio_le() virtio_legacy_is_little_endian() #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) #define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc)) #define GET_PBLOCK_DESC(x, bid) \ ((struct tpacket_block_desc *)((x)->pkbdq[(bid)].buffer)) #define GET_CURR_PBLOCK_DESC_FROM_CORE(x) \ ((struct tpacket_block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer)) #define GET_NEXT_PRB_BLK_NUM(x) \ (((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \ ((x)->kactive_blk_num+1) : 0) static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); #ifdef CONFIG_NETFILTER_EGRESS static noinline struct sk_buff *nf_hook_direct_egress(struct sk_buff *skb) { struct sk_buff *next, *head = NULL, *tail; int rc; rcu_read_lock(); for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); if (!nf_hook_egress(skb, &rc, skb->dev)) continue; if (!head) head = skb; else tail->next = skb; tail = skb; } rcu_read_unlock(); return head; } #endif static int packet_xmit(const struct packet_sock *po, struct sk_buff *skb) { if (!packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS)) return dev_queue_xmit(skb); #ifdef CONFIG_NETFILTER_EGRESS if (nf_hook_egress_active()) { skb = nf_hook_direct_egress(skb); if (!skb) return NET_XMIT_DROP; } #endif return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } static struct net_device *packet_cached_dev_get(struct packet_sock *po) { struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(po->cached_dev); dev_hold(dev); rcu_read_unlock(); return dev; } static void packet_cached_dev_assign(struct packet_sock *po, struct net_device *dev) { rcu_assign_pointer(po->cached_dev, dev); } static void packet_cached_dev_reset(struct packet_sock *po) { RCU_INIT_POINTER(po->cached_dev, NULL); } static u16 packet_pick_tx_queue(struct sk_buff *skb) { struct net_device *dev = skb->dev; const struct net_device_ops *ops = dev->netdev_ops; int cpu = raw_smp_processor_id(); u16 queue_index; #ifdef CONFIG_XPS skb->sender_cpu = cpu + 1; #endif skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues); if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb, NULL); queue_index = netdev_cap_txqueue(dev, queue_index); } else { queue_index = netdev_pick_tx(dev, skb, NULL); } return queue_index; } /* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); if (!packet_sock_flag(po, PACKET_SOCK_RUNNING)) { if (po->fanout) __fanout_link(sk, po); else dev_add_pack(&po->prot_hook); sock_hold(sk); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 1); } } static void register_prot_hook(struct sock *sk) { lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); __register_prot_hook(sk); } /* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the * callers responsibility to take care of this. */ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); lockdep_assert_held_once(&po->bind_lock); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 0); if (po->fanout) __fanout_unlink(sk, po); else __dev_remove_pack(&po->prot_hook); __sock_put(sk); if (sync) { spin_unlock(&po->bind_lock); synchronize_net(); spin_lock(&po->bind_lock); } } static void unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) __unregister_prot_hook(sk, sync); } static inline struct page * __pure pgv_to_page(void *addr) { if (is_vmalloc_addr(addr)) return vmalloc_to_page(addr); return virt_to_page(addr); } static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } smp_wmb(); } static int __packet_get_status(const struct packet_sock *po, void *frame) { union tpacket_uhdr h; smp_rmb(); /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); return 0; } } static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, unsigned int flags) { struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); if (shhwtstamps && (flags & SOF_TIMESTAMPING_RAW_HARDWARE) && ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; if ((flags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb_tstamp(skb), ts)) return TP_STATUS_TS_SOFTWARE; return 0; } static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame, struct sk_buff *skb) { union tpacket_uhdr h; struct timespec64 ts; __u32 ts_status; if (!(ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp)))) return 0; h.raw = frame; /* * versions 1 through 3 overflow the timestamps in y2106, since they * all store the seconds in a 32-bit unsigned integer. * If we create a version 4, that should have a 64-bit timestamp, * either 64-bit seconds + 32-bit nanoseconds, or just 64-bit * nanoseconds. */ switch (po->tp_version) { case TPACKET_V1: h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; break; case TPACKET_V2: h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; break; case TPACKET_V3: h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } /* one flush is safe, as both fields always lie on the same cacheline */ flush_dcache_page(pgv_to_page(&h.h1->tp_sec)); smp_wmb(); return ts_status; } static void *packet_lookup_frame(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int position, int status) { unsigned int pg_vec_pos, frame_offset; union tpacket_uhdr h; pg_vec_pos = position / rb->frames_per_block; frame_offset = position % rb->frames_per_block; h.raw = rb->pg_vec[pg_vec_pos].buffer + (frame_offset * rb->frame_size); if (status != __packet_get_status(po, h.raw)) return NULL; return h.raw; } static void *packet_current_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { return packet_lookup_frame(po, rb, rb->head, status); } static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) { u8 *skb_orig_data = skb->data; int skb_orig_len = skb->len; struct vlan_hdr vhdr, *vh; unsigned int header_len; if (!dev) return 0; /* In the SOCK_DGRAM scenario, skb data starts at the network * protocol, which is after the VLAN headers. The outer VLAN * header is at the hard_header_len offset in non-variable * length link layer headers. If it's a VLAN device, the * min_header_len should be used to exclude the VLAN header * size. */ if (dev->min_header_len == dev->hard_header_len) header_len = dev->hard_header_len; else if (is_vlan_dev(dev)) header_len = dev->min_header_len; else return 0; skb_push(skb, skb->data - skb_mac_header(skb)); vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); if (skb_orig_data != skb->data) { skb->data = skb_orig_data; skb->len = skb_orig_len; } if (unlikely(!vh)) return 0; return ntohs(vh->h_vlan_TCI); } static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) { __be16 proto = skb->protocol; if (unlikely(eth_type_vlan(proto))) { u8 *skb_orig_data = skb->data; int skb_orig_len = skb->len; skb_push(skb, skb->data - skb_mac_header(skb)); proto = __vlan_get_protocol(skb, proto, NULL); if (skb_orig_data != skb->data) { skb->data = skb_orig_data; skb->len = skb_orig_len; } } return proto; } static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { del_timer_sync(&pkc->retire_blk_timer); } static void prb_shutdown_retire_blk_timer(struct packet_sock *po, struct sk_buff_head *rb_queue) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; spin_unlock_bh(&rb_queue->lock); prb_del_retire_blk_timer(pkc); } static void prb_setup_retire_blk_timer(struct packet_sock *po) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); timer_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired, 0); pkc->retire_blk_timer.expires = jiffies; } static int prb_calc_retire_blk_tmo(struct packet_sock *po, int blk_size_in_bytes) { struct net_device *dev; unsigned int mbits, div; struct ethtool_link_ksettings ecmd; int err; rtnl_lock(); dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex); if (unlikely(!dev)) { rtnl_unlock(); return DEFAULT_PRB_RETIRE_TOV; } err = __ethtool_get_link_ksettings(dev, &ecmd); rtnl_unlock(); if (err) return DEFAULT_PRB_RETIRE_TOV; /* If the link speed is so slow you don't really * need to worry about perf anyways */ if (ecmd.base.speed < SPEED_1000 || ecmd.base.speed == SPEED_UNKNOWN) return DEFAULT_PRB_RETIRE_TOV; div = ecmd.base.speed / 1000; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); if (div) mbits /= div; if (div) return mbits + 1; return mbits; } static void prb_init_ft_ops(struct tpacket_kbdq_core *p1, union tpacket_req_u *req_u) { p1->feature_req_word = req_u->req3.tp_feature_req_word; } static void init_prb_bdqc(struct packet_sock *po, struct packet_ring_buffer *rb, struct pgv *pg_vec, union tpacket_req_u *req_u) { struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd; memset(p1, 0x0, sizeof(*p1)); p1->knxt_seq_num = 1; p1->pkbdq = pg_vec; pbd = (struct tpacket_block_desc *)pg_vec[0].buffer; p1->pkblk_start = pg_vec[0].buffer; p1->kblk_size = req_u->req3.tp_block_size; p1->knum_blocks = req_u->req3.tp_block_nr; p1->hdrlen = po->tp_hdrlen; p1->version = po->tp_version; p1->last_kactive_blk_num = 0; po->stats.stats3.tp_freeze_q_cnt = 0; if (req_u->req3.tp_retire_blk_tov) p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov; else p1->retire_blk_tov = prb_calc_retire_blk_tmo(po, req_u->req3.tp_block_size); p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; rwlock_init(&p1->blk_fill_in_prog_lock); p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); prb_setup_retire_blk_timer(po); prb_open_block(p1, pbd); } /* Do NOT update the last_blk_num first. * Assumes sk_buff_head lock is held. */ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) { mod_timer(&pkc->retire_blk_timer, jiffies + pkc->tov_in_jiffies); pkc->last_kactive_blk_num = pkc->kactive_blk_num; } /* * Timer logic: * 1) We refresh the timer only when we open a block. * By doing this we don't waste cycles refreshing the timer * on packet-by-packet basis. * * With a 1MB block-size, on a 1Gbps line, it will take * i) ~8 ms to fill a block + ii) memcpy etc. * In this cut we are not accounting for the memcpy time. * * So, if the user sets the 'tmo' to 10ms then the timer * will never fire while the block is still getting filled * (which is what we want). However, the user could choose * to close a block early and that's fine. * * But when the timer does fire, we check whether or not to refresh it. * Since the tmo granularity is in msecs, it is not too expensive * to refresh the timer, lets say every '8' msecs. * Either the user can set the 'tmo' or we can derive it based on * a) line-speed and b) block-size. * prb_calc_retire_blk_tmo() calculates the tmo. * */ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) { struct packet_sock *po = from_timer(po, t, rx_ring.prb_bdqc.retire_blk_timer); struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring); unsigned int frozen; struct tpacket_block_desc *pbd; spin_lock(&po->sk.sk_receive_queue.lock); frozen = prb_queue_frozen(pkc); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); if (unlikely(pkc->delete_blk_timer)) goto out; /* We only need to plug the race when the block is partially filled. * tpacket_rcv: * lock(); increment BLOCK_NUM_PKTS; unlock() * copy_bits() is in progress ... * timer fires on other cpu: * we can't retire the current block because copy_bits * is in progress. * */ if (BLOCK_NUM_PKTS(pbd)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) { if (!frozen) { if (!BLOCK_NUM_PKTS(pbd)) { /* An empty block. Just refresh the timer. */ goto refresh_timer; } prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO); if (!prb_dispatch_next_block(pkc, po)) goto refresh_timer; else goto out; } else { /* Case 1. Queue was frozen because user-space was * lagging behind. */ if (prb_curr_blk_in_use(pbd)) { /* * Ok, user-space is still behind. * So just refresh the timer. */ goto refresh_timer; } else { /* Case 2. queue was frozen,user-space caught up, * now the link went idle && the timer fired. * We don't have a block to close.So we open this * block and restart the timer. * opening a block thaws the queue,restarts timer * Thawing/timer-refresh is a side effect. */ prb_open_block(pkc, pbd); goto out; } } } refresh_timer: _prb_refresh_rx_retire_blk_timer(pkc); out: spin_unlock(&po->sk.sk_receive_queue.lock); } static void prb_flush_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, __u32 status) { /* Flush everything minus the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 u8 *start, *end; start = (u8 *)pbd1; /* Skip the block header(we know header WILL fit in 4K) */ start += PAGE_SIZE; end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end); for (; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif /* Now update the block status. */ BLOCK_STATUS(pbd1) = status; /* Flush the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 start = (u8 *)pbd1; flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif } /* * Side effect: * * 1) flush the block * 2) Increment active_blk_num * * Note:We DONT refresh the timer on purpose. * Because almost always the next block will be opened. */ static void prb_close_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, struct packet_sock *po, unsigned int stat) { __u32 status = TP_STATUS_USER | stat; struct tpacket3_hdr *last_pkt; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; struct sock *sk = &po->sk; if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; last_pkt = (struct tpacket3_hdr *)pkc1->prev; last_pkt->tp_next_offset = 0; /* Get the ts of the last pkt */ if (BLOCK_NUM_PKTS(pbd1)) { h1->ts_last_pkt.ts_sec = last_pkt->tp_sec; h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec; } else { /* Ok, we tmo'd - so get the current time. * * It shouldn't really happen as we don't close empty * blocks. See prb_retire_rx_blk_timer_expired(). */ struct timespec64 ts; ktime_get_real_ts64(&ts); h1->ts_last_pkt.ts_sec = ts.tv_sec; h1->ts_last_pkt.ts_nsec = ts.tv_nsec; } smp_wmb(); /* Flush the block */ prb_flush_block(pkc1, pbd1, status); sk->sk_data_ready(sk); pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1); } static void prb_thaw_queue(struct tpacket_kbdq_core *pkc) { pkc->reset_pending_on_curr_blk = 0; } /* * Side effect of opening a block: * * 1) prb_queue is thawed. * 2) retire_blk_timer is refreshed. * */ static void prb_open_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1) { struct timespec64 ts; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; smp_rmb(); /* We could have just memset this but we will lose the * flexibility of making the priv area sticky */ BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++; BLOCK_NUM_PKTS(pbd1) = 0; BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); ktime_get_real_ts64(&ts); h1->ts_first_pkt.ts_sec = ts.tv_sec; h1->ts_first_pkt.ts_nsec = ts.tv_nsec; pkc1->pkblk_start = (char *)pbd1; pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; pbd1->version = pkc1->version; pkc1->prev = pkc1->nxt_offset; pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; prb_thaw_queue(pkc1); _prb_refresh_rx_retire_blk_timer(pkc1); smp_wmb(); } /* * Queue freeze logic: * 1) Assume tp_block_nr = 8 blocks. * 2) At time 't0', user opens Rx ring. * 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7 * 4) user-space is either sleeping or processing block '0'. * 5) tpacket_rcv is currently filling block '7', since there is no space left, * it will close block-7,loop around and try to fill block '0'. * call-flow: * __packet_lookup_frame_in_block * prb_retire_current_block() * prb_dispatch_next_block() * |->(BLOCK_STATUS == USER) evaluates to true * 5.1) Since block-0 is currently in-use, we just freeze the queue. * 6) Now there are two cases: * 6.1) Link goes idle right after the queue is frozen. * But remember, the last open_block() refreshed the timer. * When this timer expires,it will refresh itself so that we can * re-open block-0 in near future. * 6.2) Link is busy and keeps on receiving packets. This is a simple * case and __packet_lookup_frame_in_block will check if block-0 * is free and can now be re-used. */ static void prb_freeze_queue(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { pkc->reset_pending_on_curr_blk = 1; po->stats.stats3.tp_freeze_q_cnt++; } #define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT)) /* * If the next block is free then we will dispatch it * and return a good offset. * Else, we will freeze the queue. * So, caller must check the return value. */ static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { struct tpacket_block_desc *pbd; smp_rmb(); /* 1. Get current block num */ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* 2. If this block is currently in_use then freeze the queue */ if (TP_STATUS_USER & BLOCK_STATUS(pbd)) { prb_freeze_queue(pkc, po); return NULL; } /* * 3. * open this block and return the offset where the first packet * needs to get stored. */ prb_open_block(pkc, pbd); return (void *)pkc->nxt_offset; } static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po, unsigned int status) { struct tpacket_block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* retire/close the current block */ if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) { /* * Plug the case where copy_bits() is in progress on * cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't * have space to copy the pkt in the current block and * called prb_retire_current_block() * * We don't need to worry about the TMO case because * the timer-handler already handled this case. */ if (!(status & TP_STATUS_BLK_TMO)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } prb_close_block(pkc, pbd, po, status); return; } } static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd) { return TP_STATUS_USER & BLOCK_STATUS(pbd); } static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) { return pkc->reset_pending_on_curr_blk; } static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) __releases(&pkc->blk_fill_in_prog_lock) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); read_unlock(&pkc->blk_fill_in_prog_lock); } static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb); } static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = 0; } static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; ppd->tp_status = TP_STATUS_AVAILABLE; } } static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_padding = 0; prb_fill_vlan_info(pkc, ppd); if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH) prb_fill_rxhash(pkc, ppd); else prb_clear_rxhash(pkc, ppd); } static void prb_fill_curr_block(char *curr, struct tpacket_kbdq_core *pkc, struct tpacket_block_desc *pbd, unsigned int len) __acquires(&pkc->blk_fill_in_prog_lock) { struct tpacket3_hdr *ppd; ppd = (struct tpacket3_hdr *)curr; ppd->tp_next_offset = TOTAL_PKT_LEN_INCL_ALIGN(len); pkc->prev = curr; pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_NUM_PKTS(pbd) += 1; read_lock(&pkc->blk_fill_in_prog_lock); prb_run_all_ft_ops(pkc, ppd); } /* Assumes caller has the sk->rx_queue.lock */ static void *__packet_lookup_frame_in_block(struct packet_sock *po, struct sk_buff *skb, unsigned int len ) { struct tpacket_kbdq_core *pkc; struct tpacket_block_desc *pbd; char *curr, *end; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* Queue is frozen when user space is lagging behind */ if (prb_queue_frozen(pkc)) { /* * Check if that last block which caused the queue to freeze, * is still in_use by user-space. */ if (prb_curr_blk_in_use(pbd)) { /* Can't record this packet */ return NULL; } else { /* * Ok, the block was released by user-space. * Now let's open that block. * opening a block also thaws the queue. * Thawing is a side effect. */ prb_open_block(pkc, pbd); } } smp_mb(); curr = pkc->nxt_offset; pkc->skb = skb; end = (char *)pbd + pkc->kblk_size; /* first try the current block */ if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) { prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* Ok, close the current block */ prb_retire_current_block(pkc, po, 0); /* Now, try to dispatch the next block */ curr = (char *)prb_dispatch_next_block(pkc, po); if (curr) { pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* * No free blocks are available.user_space hasn't caught up yet. * Queue was just frozen and now this packet will get dropped. */ return NULL; } static void *packet_current_rx_frame(struct packet_sock *po, struct sk_buff *skb, int status, unsigned int len) { char *curr = NULL; switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: curr = packet_lookup_frame(po, &po->rx_ring, po->rx_ring.head, status); return curr; case TPACKET_V3: return __packet_lookup_frame_in_block(po, skb, len); default: WARN(1, "TPACKET version not supported\n"); BUG(); return NULL; } } static void *prb_lookup_block(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int idx, int status) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx); if (status != BLOCK_STATUS(pbd)) return NULL; return pbd; } static int prb_previous_blk_num(struct packet_ring_buffer *rb) { unsigned int prev; if (rb->prb_bdqc.kactive_blk_num) prev = rb->prb_bdqc.kactive_blk_num-1; else prev = rb->prb_bdqc.knum_blocks-1; return prev; } /* Assumes caller has held the rx_queue.lock */ static void *__prb_previous_block(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = prb_previous_blk_num(rb); return prb_lookup_block(po, rb, previous, status); } static void *packet_previous_rx_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { if (po->tp_version <= TPACKET_V2) return packet_previous_frame(po, rb, status); return __prb_previous_block(po, rb, status); } static void packet_increment_rx_head(struct packet_sock *po, struct packet_ring_buffer *rb) { switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: return packet_increment_head(rb); case TPACKET_V3: default: WARN(1, "TPACKET version not supported.\n"); BUG(); return; } } static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max; return packet_lookup_frame(po, rb, previous, status); } static void packet_increment_head(struct packet_ring_buffer *buff) { buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } static void packet_inc_pending(struct packet_ring_buffer *rb) { this_cpu_inc(*rb->pending_refcnt); } static void packet_dec_pending(struct packet_ring_buffer *rb) { this_cpu_dec(*rb->pending_refcnt); } static unsigned int packet_read_pending(const struct packet_ring_buffer *rb) { unsigned int refcnt = 0; int cpu; /* We don't use pending refcount in rx_ring. */ if (rb->pending_refcnt == NULL) return 0; for_each_possible_cpu(cpu) refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu); return refcnt; } static int packet_alloc_pending(struct packet_sock *po) { po->rx_ring.pending_refcnt = NULL; po->tx_ring.pending_refcnt = alloc_percpu(unsigned int); if (unlikely(po->tx_ring.pending_refcnt == NULL)) return -ENOBUFS; return 0; } static void packet_free_pending(struct packet_sock *po) { free_percpu(po->tx_ring.pending_refcnt); } #define ROOM_POW_OFF 2 #define ROOM_NONE 0x0 #define ROOM_LOW 0x1 #define ROOM_NORMAL 0x2 static bool __tpacket_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.frame_max) + 1; idx = READ_ONCE(po->rx_ring.head); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks); idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static int __packet_rcv_has_room(const struct packet_sock *po, const struct sk_buff *skb) { const struct sock *sk = &po->sk; int ret = ROOM_NONE; if (po->prot_hook.func != tpacket_rcv) { int rcvbuf = READ_ONCE(sk->sk_rcvbuf); int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc) - (skb ? skb->truesize : 0); if (avail > (rcvbuf >> ROOM_POW_OFF)) return ROOM_NORMAL; else if (avail > 0) return ROOM_LOW; else return ROOM_NONE; } if (po->tp_version == TPACKET_V3) { if (__tpacket_v3_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_v3_has_room(po, 0)) ret = ROOM_LOW; } else { if (__tpacket_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_has_room(po, 0)) ret = ROOM_LOW; } return ret; } static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { bool pressure; int ret; ret = __packet_rcv_has_room(po, skb); pressure = ret != ROOM_NORMAL; if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) != pressure) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, pressure); return ret; } static void packet_rcv_try_clear_pressure(struct packet_sock *po) { if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false); } static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive packet socket: %p\n", sk); return; } } static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) { u32 *history = po->rollover->history; u32 victim, rxhash; int i, count = 0; rxhash = skb_get_hash(skb); for (i = 0; i < ROLLOVER_HLEN; i++) if (READ_ONCE(history[i]) == rxhash) count++; victim = get_random_u32_below(ROLLOVER_HLEN); /* Avoid dirtying the cache line if possible */ if (READ_ONCE(history[victim]) != rxhash) WRITE_ONCE(history[victim], rxhash); return count > (ROLLOVER_HLEN >> 1); } static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { unsigned int val = atomic_inc_return(&f->rr_cur); return val % num; } static unsigned int fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return smp_processor_id() % num; } static unsigned int fanout_demux_rnd(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return get_random_u32_below(num); } static unsigned int fanout_demux_rollover(struct packet_fanout *f, struct sk_buff *skb, unsigned int idx, bool try_self, unsigned int num) { struct packet_sock *po, *po_next, *po_skip = NULL; unsigned int i, j, room = ROOM_NONE; po = pkt_sk(rcu_dereference(f->arr[idx])); if (try_self) { room = packet_rcv_has_room(po, skb); if (room == ROOM_NORMAL || (room == ROOM_LOW && !fanout_flow_is_huge(po, skb))) return idx; po_skip = po; } i = j = min_t(int, po->rollover->sock, num - 1); do { po_next = pkt_sk(rcu_dereference(f->arr[i])); if (po_next != po_skip && !packet_sock_flag(po_next, PACKET_SOCK_PRESSURE) && packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) po->rollover->sock = i; atomic_long_inc(&po->rollover->num); if (room == ROOM_LOW) atomic_long_inc(&po->rollover->num_huge); return i; } if (++i == num) i = 0; } while (i != j); atomic_long_inc(&po->rollover->num_failed); return idx; } static unsigned int fanout_demux_qm(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return skb_get_queue_mapping(skb) % num; } static unsigned int fanout_demux_bpf(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { struct bpf_prog *prog; unsigned int ret = 0; rcu_read_lock(); prog = rcu_dereference(f->bpf_prog); if (prog) ret = bpf_prog_run_clear_cb(prog, skb) % num; rcu_read_unlock(); return ret; } static bool fanout_has_flag(struct packet_fanout *f, u16 flag) { return f->flags & (flag >> 8); } static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct packet_fanout *f = pt->af_packet_priv; unsigned int num = READ_ONCE(f->num_members); struct net *net = read_pnet(&f->net); struct packet_sock *po; unsigned int idx; if (!net_eq(dev_net(dev), net) || !num) { kfree_skb(skb); return 0; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) { skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET); if (!skb) return 0; } switch (f->type) { case PACKET_FANOUT_HASH: default: idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: idx = fanout_demux_lb(f, skb, num); break; case PACKET_FANOUT_CPU: idx = fanout_demux_cpu(f, skb, num); break; case PACKET_FANOUT_RND: idx = fanout_demux_rnd(f, skb, num); break; case PACKET_FANOUT_QM: idx = fanout_demux_qm(f, skb, num); break; case PACKET_FANOUT_ROLLOVER: idx = fanout_demux_rollover(f, skb, 0, false, num); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: idx = fanout_demux_bpf(f, skb, num); break; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER)) idx = fanout_demux_rollover(f, skb, idx, true, num); po = pkt_sk(rcu_dereference(f->arr[idx])); return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } DEFINE_MUTEX(fanout_mutex); EXPORT_SYMBOL_GPL(fanout_mutex); static LIST_HEAD(fanout_list); static u16 fanout_next_id; static void __fanout_link(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; spin_lock(&f->lock); rcu_assign_pointer(f->arr[f->num_members], sk); smp_wmb(); f->num_members++; if (f->num_members == 1) dev_add_pack(&f->prot_hook); spin_unlock(&f->lock); } static void __fanout_unlink(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; int i; spin_lock(&f->lock); for (i = 0; i < f->num_members; i++) { if (rcu_dereference_protected(f->arr[i], lockdep_is_held(&f->lock)) == sk) break; } BUG_ON(i >= f->num_members); rcu_assign_pointer(f->arr[i], rcu_dereference_protected(f->arr[f->num_members - 1], lockdep_is_held(&f->lock))); f->num_members--; if (f->num_members == 0) __dev_remove_pack(&f->prot_hook); spin_unlock(&f->lock); } static bool match_fanout_group(struct packet_type *ptype, struct sock *sk) { if (sk->sk_family != PF_PACKET) return false; return ptype->af_packet_priv == pkt_sk(sk)->fanout; } static void fanout_init_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_LB: atomic_set(&f->rr_cur, 0); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: RCU_INIT_POINTER(f->bpf_prog, NULL); break; } } static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new) { struct bpf_prog *old; spin_lock(&f->lock); old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock)); rcu_assign_pointer(f->bpf_prog, new); spin_unlock(&f->lock); if (old) { synchronize_net(); bpf_prog_destroy(old); } } static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; struct sock_fprog fprog; int ret; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; ret = copy_bpf_fprog_from_user(&fprog, data, len); if (ret) return ret; ret = bpf_prog_create_from_user(&new, &fprog, NULL, false); if (ret) return ret; __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data_ebpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; u32 fd; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; if (len != sizeof(fd)) return -EINVAL; if (copy_from_sockptr(&fd, data, len)) return -EFAULT; new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(new)) return PTR_ERR(new); __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data(struct packet_sock *po, sockptr_t data, unsigned int len) { switch (po->fanout->type) { case PACKET_FANOUT_CBPF: return fanout_set_data_cbpf(po, data, len); case PACKET_FANOUT_EBPF: return fanout_set_data_ebpf(po, data, len); default: return -EINVAL; } } static void fanout_release_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: __fanout_set_data_bpf(f, NULL); } } static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id) { struct packet_fanout *f; list_for_each_entry(f, &fanout_list, list) { if (f->id == candidate_id && read_pnet(&f->net) == sock_net(sk)) { return false; } } return true; } static bool fanout_find_new_id(struct sock *sk, u16 *new_id) { u16 id = fanout_next_id; do { if (__fanout_id_is_free(sk, id)) { *new_id = id; fanout_next_id = id + 1; return true; } id++; } while (id != fanout_next_id); return false; } static int fanout_add(struct sock *sk, struct fanout_args *args) { struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); u16 type_flags = args->type_flags; struct packet_fanout *f, *match; u8 type = type_flags & 0xff; u8 flags = type_flags >> 8; u16 id = args->id; int err; switch (type) { case PACKET_FANOUT_ROLLOVER: if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER) return -EINVAL; break; case PACKET_FANOUT_HASH: case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: case PACKET_FANOUT_RND: case PACKET_FANOUT_QM: case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: break; default: return -EINVAL; } mutex_lock(&fanout_mutex); err = -EALREADY; if (po->fanout) goto out; if (type == PACKET_FANOUT_ROLLOVER || (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) { err = -ENOMEM; rollover = kzalloc(sizeof(*rollover), GFP_KERNEL); if (!rollover) goto out; atomic_long_set(&rollover->num, 0); atomic_long_set(&rollover->num_huge, 0); atomic_long_set(&rollover->num_failed, 0); } if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) { if (id != 0) { err = -EINVAL; goto out; } if (!fanout_find_new_id(sk, &id)) { err = -ENOMEM; goto out; } /* ephemeral flag for the first socket in the group: drop it */ flags &= ~(PACKET_FANOUT_FLAG_UNIQUEID >> 8); } match = NULL; list_for_each_entry(f, &fanout_list, list) { if (f->id == id && read_pnet(&f->net) == sock_net(sk)) { match = f; break; } } err = -EINVAL; if (match) { if (match->flags != flags) goto out; if (args->max_num_members && args->max_num_members != match->max_num_members) goto out; } else { if (args->max_num_members > PACKET_FANOUT_MAX) goto out; if (!args->max_num_members) /* legacy PACKET_FANOUT_MAX */ args->max_num_members = 256; err = -ENOMEM; match = kvzalloc(struct_size(match, arr, args->max_num_members), GFP_KERNEL); if (!match) goto out; write_pnet(&match->net, sock_net(sk)); match->id = id; match->type = type; match->flags = flags; INIT_LIST_HEAD(&match->list); spin_lock_init(&match->lock); refcount_set(&match->sk_ref, 0); fanout_init_data(match); match->prot_hook.type = po->prot_hook.type; match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; match->prot_hook.ignore_outgoing = type_flags & PACKET_FANOUT_FLAG_IGNORE_OUTGOING; list_add(&match->list, &fanout_list); } err = -EINVAL; spin_lock(&po->bind_lock); if (packet_sock_flag(po, PACKET_SOCK_RUNNING) && match->type == type && match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; if (refcount_read(&match->sk_ref) < match->max_num_members) { __dev_remove_pack(&po->prot_hook); /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ WRITE_ONCE(po->fanout, match); po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); __fanout_link(sk, po); err = 0; } } spin_unlock(&po->bind_lock); if (err && !refcount_read(&match->sk_ref)) { list_del(&match->list); kvfree(match); } out: kfree(rollover); mutex_unlock(&fanout_mutex); return err; } /* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout. * It is the responsibility of the caller to call fanout_release_data() and * free the returned packet_fanout (after synchronize_net()) */ static struct packet_fanout *fanout_release(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f; mutex_lock(&fanout_mutex); f = po->fanout; if (f) { po->fanout = NULL; if (refcount_dec_and_test(&f->sk_ref)) list_del(&f->list); else f = NULL; } mutex_unlock(&fanout_mutex); return f; } static bool packet_extra_vlan_len_allowed(const struct net_device *dev, struct sk_buff *skb) { /* Earlier code assumed this would be a VLAN pkt, double-check * this now that we have the actual packet in hand. We can only * do this check on Ethernet devices. */ if (unlikely(dev->type != ARPHRD_ETHER)) return false; skb_reset_mac_header(skb); return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)); } static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; struct sockaddr_pkt *spkt; /* * When we registered the protocol we saved the socket in the data * field for just this event. */ sk = pt->af_packet_priv; /* * Yank back the headers [hope the device set this * right or kerboom...] * * Incoming packets have ll header pulled, * push it back. * * For outgoing ones skb->data == skb_mac_header(skb) * so that this procedure is noop. */ if (skb->pkt_type == PACKET_LOOPBACK) goto out; if (!net_eq(dev_net(dev), sock_net(sk))) goto out; skb = skb_share_check(skb, GFP_ATOMIC); if (skb == NULL) goto oom; /* drop any routing info */ skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spkt = &PACKET_SKB_CB(skb)->sa.pkt; skb_push(skb, skb->data - skb_mac_header(skb)); /* * The SOCK_PACKET socket receives _all_ frames. */ spkt->spkt_family = dev->type; strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); spkt->spkt_protocol = skb->protocol; /* * Charge the memory to the socket. This is done specifically * to prevent sockets using all the memory up. */ if (sock_queue_rcv_skb(sk, skb) == 0) return 0; out: kfree_skb(skb); oom: return 0; } static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { int depth; if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && sock->type == SOCK_RAW) { skb_reset_mac_header(skb); skb->protocol = dev_parse_header_protocol(skb); } /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); skb_probe_transport_header(skb); } /* * Output a raw packet to a device layer. This bypasses all the other * protocol layers and you must therefore supply it with a complete frame */ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); struct sk_buff *skb = NULL; struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; int err; int extra_len = 0; /* * Get and verify the address. */ if (saddr) { if (msg->msg_namelen < sizeof(struct sockaddr)) return -EINVAL; if (msg->msg_namelen == sizeof(struct sockaddr_pkt)) proto = saddr->spkt_protocol; } else return -ENOTCONN; /* SOCK_PACKET must be sent giving an address */ /* * Find the device first to size check it */ saddr->spkt_device[sizeof(saddr->spkt_device) - 1] = 0; retry: rcu_read_lock(); dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device); err = -ENODEV; if (dev == NULL) goto out_unlock; err = -ENETDOWN; if (!(dev->flags & IFF_UP)) goto out_unlock; /* * You may not queue a frame bigger than the mtu. This is the lowest level * raw protocol and you must do your own fragmentation at this level. */ if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { size_t reserved = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); if (skb == NULL) return -ENOBUFS; /* FIXME: Save some space for broken drivers that write a hard * header at transmission time by themselves. PPP is the notable * one here. This should really be fixed at the driver level. */ skb_reserve(skb, reserved); skb_reset_network_header(skb); /* Try to align data part correctly */ if (hhlen) { skb->data -= hhlen; skb->tail -= hhlen; if (len < hhlen) skb_reset_network_header(skb); } err = memcpy_from_msg(skb_put(skb, len), msg, len); if (err) goto out_free; goto retry; } if (!dev_validate_header(dev, skb->data, len) || !skb->len) { err = -EINVAL; goto out_unlock; } if (len > (dev->mtu + dev->hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); dev_queue_xmit(skb); rcu_read_unlock(); return len; out_unlock: rcu_read_unlock(); out_free: kfree_skb(skb); return err; } static unsigned int run_filter(struct sk_buff *skb, const struct sock *sk, unsigned int res) { struct sk_filter *filter; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) res = bpf_prog_run_clear_cb(filter->prog, skb); rcu_read_unlock(); return res; } static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, size_t *len, int vnet_hdr_sz) { struct virtio_net_hdr_mrg_rxbuf vnet_hdr = { .num_buffers = 0 }; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)&vnet_hdr, vio_le(), true, 0)) return -EINVAL; return memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_sz); } /* * This function makes lazy skb cloning in hope that most of packets * are discarded by BPF. * * Note tricky part: we DO mangle shared skb! skb->data, skb->len * and skb->cb are mangled. It works because (and until) packets * falling here are owned by current CPU. Output packets are cloned * by dev_queue_xmit_nit(), input packets are processed by net_bh * sequentially, so that if we return skb to original state on exit, * we will not harm anyone. */ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; skb->dev = dev; if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * * Otherwise, the device hides details of its frame * structure, so that corresponding packet head is * never delivered to user. */ if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb->len; res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; if (snaplen > res) snaplen = res; if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto drop_n_acct; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (nskb == NULL) goto drop_n_acct; if (skb_head != skb->data) { skb->data = skb_head; skb->len = skb_len; } consume_skb(skb); skb = nskb; } sock_skb_cb_check_size(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8); sll = &PACKET_SKB_CB(skb)->sa.ll; sll->sll_hatype = dev->type; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; sll->sll_halen = dev_parse_header(skb, sll->sll_addr); /* sll->sll_family and sll->sll_protocol are set in packet_recvmsg(). * Use their space for storing the original skb length. */ PACKET_SKB_CB(skb)->sa.origlen = skb->len; if (pskb_trim(skb, snaplen)) goto drop_n_acct; skb_set_owner_r(skb, sk); skb->dev = NULL; skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; sock_skb_set_dropcount(sk, skb); skb_clear_delivery_time(skb); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); return 0; drop_n_acct: atomic_inc(&po->tp_drops); atomic_inc(&sk->sk_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; } static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct packet_sock *po; struct sockaddr_ll *sll; union tpacket_uhdr h; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; unsigned short macoff, hdrlen; unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; unsigned int slot_id = 0; int vnet_hdr_sz = 0; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. * We may add members to them until current aligned size without forcing * userspace to call getsockopt(..., PACKET_HDRLEN, ...). */ BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32); BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48); if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb->len; res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; /* If we are flooded, just give up */ if (__packet_rcv_has_room(po, skb) == ROOM_NONE) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) status |= TP_STATUS_GSO_TCP; if (snaplen > res) snaplen = res; if (sk->sk_type == SOCK_DGRAM) { macoff = netoff = TPACKET_ALIGN(po->tp_hdrlen) + 16 + po->tp_reserve; } else { unsigned int maclen = skb_network_offset(skb); netoff = TPACKET_ALIGN(po->tp_hdrlen + (maclen < 16 ? 16 : maclen)) + po->tp_reserve; vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); if (vnet_hdr_sz) netoff += vnet_hdr_sz; macoff = netoff - maclen; } if (netoff > USHRT_MAX) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (READ_ONCE(po->copy_thresh) && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); } else { copy_skb = skb_get(skb); skb_head = skb->data; } if (copy_skb) { memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0, sizeof(PACKET_SKB_CB(copy_skb)->sa.ll)); skb_set_owner_r(copy_skb, sk); } } snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) { snaplen = 0; vnet_hdr_sz = 0; } } } else if (unlikely(macoff + snaplen > GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { u32 nval; nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", snaplen, nval, macoff); snaplen = nval; if (unlikely((int)snaplen < 0)) { snaplen = 0; macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; vnet_hdr_sz = 0; } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; if (po->tp_version <= TPACKET_V2) { slot_id = po->rx_ring.head; if (test_bit(slot_id, po->rx_ring.rx_owner_map)) goto drop_n_account; __set_bit(slot_id, po->rx_ring.rx_owner_map); } if (vnet_hdr_sz && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), vio_le(), true, 0)) { if (po->tp_version == TPACKET_V3) prb_clear_blk_fill_status(&po->rx_ring); goto drop_n_account; } if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* * LOSING will be reported till you read the stats, * because it's COR - Clear On Read. * Anyways, moving it for V1/V2 only as V3 doesn't need this * at packet level. */ if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; } po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; skb_clear_delivery_time(copy_skb); __skb_queue_tail(&sk->sk_receive_queue, copy_skb); } spin_unlock(&sk->sk_receive_queue.lock); skb_copy_bits(skb, 0, h.raw + macoff, snaplen); /* Always timestamp; prefer an existing software timestamp taken * closer to the time of capture. */ ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp) | SOF_TIMESTAMPING_SOFTWARE); if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; switch (po->tp_version) { case TPACKET_V1: h.h1->tp_len = skb->len; h.h1->tp_snaplen = snaplen; h.h1->tp_mac = macoff; h.h1->tp_net = netoff; h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; hdrlen = sizeof(*h.h1); break; case TPACKET_V2: h.h2->tp_len = skb->len; h.h2->tp_snaplen = snaplen; h.h2->tp_mac = macoff; h.h2->tp_net = netoff; h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; if (skb_vlan_tag_present(skb)) { h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); h.h2->tp_vlan_tpid = ntohs(skb->protocol); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; } memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding)); hdrlen = sizeof(*h.h2); break; case TPACKET_V3: /* tp_nxt_offset,vlan are already populated above. * So DONT clear those fields here */ h.h3->tp_status |= status; h.h3->tp_len = skb->len; h.h3->tp_snaplen = snaplen; h.h3->tp_mac = macoff; h.h3->tp_net = netoff; h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding)); hdrlen = sizeof(*h.h3); break; default: BUG(); } sll = h.raw + TPACKET_ALIGN(hdrlen); sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; smp_mb(); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 if (po->tp_version <= TPACKET_V2) { u8 *start, *end; end = (u8 *) PAGE_ALIGN((unsigned long) h.raw + macoff + snaplen); for (start = h.raw; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); } smp_wmb(); #endif if (po->tp_version <= TPACKET_V2) { spin_lock(&sk->sk_receive_queue.lock); __packet_set_status(po, h.raw, status); __clear_bit(slot_id, po->rx_ring.rx_owner_map); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); } else if (po->tp_version == TPACKET_V3) { prb_clear_blk_fill_status(&po->rx_ring); } drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; drop_n_account: spin_unlock(&sk->sk_receive_queue.lock); atomic_inc(&po->tp_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); sk_skb_reason_drop(sk, copy_skb, drop_reason); goto drop_n_restore; } static void tpacket_destruct_skb(struct sk_buff *skb) { struct packet_sock *po = pkt_sk(skb->sk); if (likely(po->tx_ring.pg_vec)) { void *ph; __u32 ts; ph = skb_zcopy_get_nouarg(skb); packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); complete(&po->skb_completion); } sock_wfree(skb); } static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len) { if ((vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && (__virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2 > __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len))) vnet_hdr->hdr_len = __cpu_to_virtio16(vio_le(), __virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2); if (__virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len) > len) return -EINVAL; return 0; } static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, struct virtio_net_hdr *vnet_hdr, int vnet_hdr_sz) { int ret; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (!copy_from_iter_full(vnet_hdr, sizeof(*vnet_hdr), &msg->msg_iter)) return -EFAULT; ret = __packet_snd_vnet_parse(vnet_hdr, *len); if (ret) return ret; /* move iter to point to the start of mac header */ if (vnet_hdr_sz != sizeof(struct virtio_net_hdr)) iov_iter_advance(&msg->msg_iter, vnet_hdr_sz - sizeof(struct virtio_net_hdr)); return 0; } static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; int to_write, offset, len, nr_frags, len_max; struct socket *sock = po->sk.sk_socket; struct page *page; int err; ph.raw = frame; skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid); skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); skb_reset_network_header(skb); to_write = tp_len; if (sock->type == SOCK_DGRAM) { err = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, tp_len); if (unlikely(err < 0)) return -EINVAL; } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); skb_push(skb, dev->hard_header_len); skb_put(skb, copylen - dev->hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; if (!dev_validate_header(dev, skb->data, hdrlen)) return -EINVAL; data += hdrlen; to_write -= hdrlen; } offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); skb->data_len = to_write; skb->len += to_write; skb->truesize += to_write; refcount_add(to_write, &po->sk.sk_wmem_alloc); while (likely(to_write)) { nr_frags = skb_shinfo(skb)->nr_frags; if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { pr_err("Packet exceed the number of skb frags(%u)\n", (unsigned int)MAX_SKB_FRAGS); return -EFAULT; } page = pgv_to_page(data); data += len; flush_dcache_page(page); get_page(page); skb_fill_page_desc(skb, nr_frags, page, offset, len); to_write -= len; offset = 0; len_max = PAGE_SIZE; len = ((to_write > len_max) ? len_max : to_write); } packet_parse_headers(skb, sock); return tp_len; } static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; int tp_len, off; ph.raw = frame; switch (po->tp_version) { case TPACKET_V3: if (ph.h3->tp_next_offset != 0) { pr_warn_once("variable sized slot not supported"); return -EINVAL; } tp_len = ph.h3->tp_len; break; case TPACKET_V2: tp_len = ph.h2->tp_len; break; default: tp_len = ph.h1->tp_len; break; } if (unlikely(tp_len > size_max)) { pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); return -EMSGSIZE; } if (unlikely(packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF))) { int off_min, off_max; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); off_max = po->tx_ring.frame_size - tp_len; if (po->sk.sk_type == SOCK_DGRAM) { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_net; break; case TPACKET_V2: off = ph.h2->tp_net; break; default: off = ph.h1->tp_net; break; } } else { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_mac; break; case TPACKET_V2: off = ph.h2->tp_mac; break; default: off = ph.h1->tp_mac; break; } } if (unlikely((off < off_min) || (off_max < off))) return -EINVAL; } else { off = po->tp_hdrlen - sizeof(struct sockaddr_ll); } *data = frame + off; return tp_len; } static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { struct sk_buff *skb = NULL; struct net_device *dev; struct virtio_net_hdr *vnet_hdr = NULL; struct sockcm_cookie sockc; __be16 proto; int err, reserve = 0; void *ph; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); unsigned char *addr = NULL; int tp_len, size_max; void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; long timeo = 0; mutex_lock(&po->pg_vec_lock); /* packet_sendmsg() check on tx_ring.pg_vec was lockless, * we need to confirm it under protection of pg_vec_lock. */ if (unlikely(!po->tx_ring.pg_vec)) { err = -EBUSY; goto out; } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); if (po->sk.sk_socket->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_put; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; sockcm_init(&sockc, &po->sk); if (msg->msg_controllen) { err = sock_cmsg_send(&po->sk, msg, &sockc); if (unlikely(err)) goto out_put; } if (po->sk.sk_socket->type == SOCK_RAW) reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !vnet_hdr_sz) size_max = dev->mtu + reserve + VLAN_HLEN; reinit_completion(&po->skb_completion); do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { if (need_wait && skb) { timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); if (timeo <= 0) { err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; goto out_put; } } /* check for additional frames */ continue; } skb = NULL; tp_len = tpacket_parse_header(po, ph, size_max, &data); if (tp_len < 0) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { vnet_hdr = data; data += vnet_hdr_sz; tp_len -= vnet_hdr_sz; if (tp_len < 0 || __packet_snd_vnet_parse(vnet_hdr, tp_len)) { tp_len = -EINVAL; goto tpacket_error; } copylen = __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len); } copylen = max_t(int, copylen, dev->hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + (copylen - dev->hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { /* we assume the socket was initially writeable ... */ if (likely(len_sum > 0)) err = len_sum; goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, addr, hlen, copylen, &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz && !packet_extra_vlan_len_allowed(dev, skb)) tp_len = -EMSGSIZE; if (unlikely(tp_len < 0)) { tpacket_error: if (packet_sock_flag(po, PACKET_SOCK_TP_LOSS)) { __packet_set_status(po, ph, TP_STATUS_AVAILABLE); packet_increment_head(&po->tx_ring); kfree_skb(skb); continue; } else { status = TP_STATUS_WRONG_FORMAT; err = tp_len; goto out_status; } } if (vnet_hdr_sz) { if (virtio_net_hdr_to_skb(skb, vnet_hdr, vio_le())) { tp_len = -EINVAL; goto tpacket_error; } virtio_net_hdr_set_proto(skb, vnet_hdr); } skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); status = TP_STATUS_SEND_REQUEST; err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ skb = NULL; goto out_status; } /* * skb was dropped but not destructed yet; * let's treat it like congestion or err < 0 */ err = 0; } packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (likely((ph != NULL) || /* Note: packet_read_pending() might be slow if we have * to call it as it's per_cpu variable, but in fast-path * we already short-circuit the loop with the first * condition, and luckily don't have to go that path * anyway. */ (need_wait && packet_read_pending(&po->tx_ring)))); err = len_sum; goto out_put; out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; } static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, size_t reserve, size_t len, size_t linear, int noblock, int *err) { struct sk_buff *skb; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE || !linear) linear = len; if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER); skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, err, PAGE_ALLOC_COSTLY_ORDER); if (!skb) return NULL; skb_reserve(skb, reserve); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); struct sk_buff *skb; struct net_device *dev; __be16 proto; unsigned char *addr = NULL; int err, reserve = 0; struct sockcm_cookie sockc; struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); int hlen, tlen, linear; int extra_len = 0; /* * Get and verify the address. */ if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); if (sock->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_unlock; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out_unlock; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; sockcm_init(&sockc, sk); sockc.mark = READ_ONCE(sk->sk_mark); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } if (sock->type == SOCK_RAW) reserve = dev->hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) goto out_unlock; } if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + VLAN_HLEN + extra_len)) goto out_unlock; err = -ENOBUFS; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); linear = max(linear, min_t(int, len, dev->hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; skb_reset_network_header(skb); err = -EINVAL; if (sock->type == SOCK_DGRAM) { offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && dev->min_header_len != dev->hard_header_len) skb_reset_network_header(skb); } /* Returns -EFAULT on error */ err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len); if (err) goto out_free; if ((sock->type == SOCK_RAW && !dev_validate_header(dev, skb->data, len)) || !skb->len) { err = -EINVAL; goto out_free; } skb_setup_tx_timestamp(skb, sockc.tsflags); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_free; } skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); if (vnet_hdr_sz) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; len += vnet_hdr_sz; virtio_net_hdr_set_proto(skb, &vnet_hdr); } err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err) goto out_unlock; } dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: dev_put(dev); out: return err; } static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. * tpacket_snd() will redo the check safely. */ if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); return packet_snd(sock, msg, len); } /* * Close a PACKET socket. This is fairly simple. We immediately go * to 'closed' state and remove our protocol entry in the device list. */ static int packet_release(struct socket *sock) { struct sock *sk = sock->sk; struct packet_sock *po; struct packet_fanout *f; struct net *net; union tpacket_req_u req_u; if (!sk) return 0; net = sock_net(sk); po = pkt_sk(sk); mutex_lock(&net->packet.sklist_lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); packet_cached_dev_reset(po); if (po->prot_hook.dev) { netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); packet_flush_mclist(sk); lock_sock(sk); if (po->rx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); } if (po->tx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); } release_sock(sk); f = fanout_release(sk); synchronize_net(); kfree(po->rollover); if (f) { fanout_release_data(f); kvfree(f); } /* * Now the socket is dead. No more input will appear. */ sock_orphan(sk); sock->sk = NULL; /* Purge queues */ skb_queue_purge(&sk->sk_receive_queue); packet_free_pending(po); sock_put(sk); return 0; } /* * Attach a packet hook. */ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, __be16 proto) { struct packet_sock *po = pkt_sk(sk); struct net_device *dev = NULL; bool unlisted = false; bool need_rehook; int ret = 0; lock_sock(sk); spin_lock(&po->bind_lock); if (!proto) proto = po->num; rcu_read_lock(); if (po->fanout) { ret = -EINVAL; goto out_unlock; } if (name) { dev = dev_get_by_name_rcu(sock_net(sk), name); if (!dev) { ret = -ENODEV; goto out_unlock; } } else if (ifindex) { dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (!dev) { ret = -ENODEV; goto out_unlock; } } need_rehook = po->prot_hook.type != proto || po->prot_hook.dev != dev; if (need_rehook) { dev_hold(dev); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { rcu_read_unlock(); /* prevents packet_notifier() from calling * register_prot_hook() */ WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); if (dev) unlisted = !dev_get_by_index_rcu(sock_net(sk), dev->ifindex); } BUG_ON(packet_sock_flag(po, PACKET_SOCK_RUNNING)); WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); if (unlikely(unlisted)) { po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { netdev_hold(dev, &po->prot_hook.dev_tracker, GFP_ATOMIC); po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } dev_put(dev); } if (proto == 0 || !need_rehook) goto out_unlock; if (!unlisted && (!dev || (dev->flags & IFF_UP))) { register_prot_hook(sk); } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } out_unlock: rcu_read_unlock(); spin_unlock(&po->bind_lock); release_sock(sk); return ret; } /* * Bind a packet socket to a device */ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality */ if (addr_len != sizeof(struct sockaddr)) return -EINVAL; /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr; struct sock *sk = sock->sk; /* * Check legality */ if (addr_len < sizeof(struct sockaddr_ll)) return -EINVAL; if (sll->sll_family != AF_PACKET) return -EINVAL; return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { .name = "PACKET", .owner = THIS_MODULE, .obj_size = sizeof(struct packet_sock), }; /* * Create a packet of type SOCK_PACKET. */ static int packet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct packet_sock *po; __be16 proto = (__force __be16)protocol; /* weird, but documented */ int err; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW && sock->type != SOCK_PACKET) return -ESOCKTNOSUPPORT; sock->state = SS_UNCONNECTED; err = -ENOBUFS; sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto, kern); if (sk == NULL) goto out; sock->ops = &packet_ops; if (sock->type == SOCK_PACKET) sock->ops = &packet_ops_spkt; sock_init_data(sock, sk); po = pkt_sk(sk); init_completion(&po->skb_completion); sk->sk_family = PF_PACKET; po->num = proto; err = packet_alloc_pending(po); if (err) goto out2; packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; /* * Attach a protocol block */ spin_lock_init(&po->bind_lock); mutex_init(&po->pg_vec_lock); po->rollover = NULL; po->prot_hook.func = packet_rcv; if (sock->type == SOCK_PACKET) po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, &packet_proto, 1); return 0; out2: sk_free(sk); out: return err; } /* * Pull a packet from our receive queue and hand it to the user. * If necessary we block. */ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; int vnet_hdr_len = READ_ONCE(pkt_sk(sk)->vnet_hdr_sz); unsigned int origlen = 0; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE)) goto out; #if 0 /* What error should we return now? EUNATTACH? */ if (pkt_sk(sk)->ifindex < 0) return -ENODEV; #endif if (flags & MSG_ERRQUEUE) { err = sock_recv_errqueue(sk, msg, len, SOL_PACKET, PACKET_TX_TIMESTAMP); goto out; } /* * Call the generic datagram receiver. This handles all sorts * of horrible races and re-entrancy so we can forget about it * in the protocol layers. * * Now it will return ENETDOWN, if device have just gone down, * but then it will block. */ skb = skb_recv_datagram(sk, flags, &err); /* * An error occurred so return it. Because skb_recv_datagram() * handles the blocking we don't see and worry about blocking * retries. */ if (skb == NULL) goto out; packet_rcv_try_clear_pressure(pkt_sk(sk)); if (vnet_hdr_len) { err = packet_rcv_vnet(msg, skb, &len, vnet_hdr_len); if (err) goto out_free; } /* You lose any data beyond the buffer you gave. If it worries * a user program they can ask the device for its MTU * anyway. */ copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free; if (sock->type != SOCK_PACKET) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; sll->sll_protocol = (sock->type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { const size_t max_len = min(sizeof(skb->cb), sizeof(struct sockaddr_storage)); int copy_len; /* If the address length field is there to be filled * in, we fill it in now. */ if (sock->type == SOCK_PACKET) { __sockaddr_check_size(sizeof(struct sockaddr_pkt)); msg->msg_namelen = sizeof(struct sockaddr_pkt); copy_len = msg->msg_namelen; } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); copy_len = msg->msg_namelen; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) { memset(msg->msg_name + offsetof(struct sockaddr_ll, sll_addr), 0, sizeof(sll->sll_addr)); msg->msg_namelen = sizeof(struct sockaddr_ll); } } if (WARN_ON_ONCE(copy_len > max_len)) { copy_len = max_len; msg->msg_namelen = copy_len; } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } if (packet_sock_flag(pkt_sk(sk), PACKET_SOCK_AUXDATA)) { struct tpacket_auxdata aux; aux.tp_status = TP_STATUS_USER; if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) aux.tp_status |= TP_STATUS_GSO_TCP; aux.tp_len = origlen; aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); if (skb_vlan_tag_present(skb)) { aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); if (dev) { aux.tp_vlan_tci = vlan_get_tci(skb, dev); aux.tp_vlan_tpid = ntohs(skb->protocol); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } /* * Free or return the buffer as appropriate. Again this * hides all the races and re-entrancy issues from us. */ err = vnet_hdr_len + ((flags&MSG_TRUNC) ? skb->len : copied); out_free: skb_free_datagram(sk, skb); out: return err; } static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; if (peer) return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); } static int packet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); int ifindex; if (peer) return -EOPNOTSUPP; ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; /* Let __fortify_memcpy_chk() know the actual buffer size. */ memcpy(((struct sockaddr_storage *)sll)->__data + offsetof(struct sockaddr_ll, sll_addr) - offsetofend(struct sockaddr_ll, sll_family), dev->dev_addr, dev->addr_len); } else { sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */ sll->sll_halen = 0; } rcu_read_unlock(); return offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; } static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, int what) { switch (i->type) { case PACKET_MR_MULTICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_mc_add(dev, i->addr); else return dev_mc_del(dev, i->addr); break; case PACKET_MR_PROMISC: return dev_set_promiscuity(dev, what); case PACKET_MR_ALLMULTI: return dev_set_allmulti(dev, what); case PACKET_MR_UNICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_uc_add(dev, i->addr); else return dev_uc_del(dev, i->addr); break; default: break; } return 0; } static void packet_dev_mclist_delete(struct net_device *dev, struct packet_mclist **mlp) { struct packet_mclist *ml; while ((ml = *mlp) != NULL) { if (ml->ifindex == dev->ifindex) { packet_dev_mc(dev, ml, -1); *mlp = ml->next; kfree(ml); } else mlp = &ml->next; } } static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml, *i; struct net_device *dev; int err; rtnl_lock(); err = -ENODEV; dev = __dev_get_by_index(sock_net(sk), mreq->mr_ifindex); if (!dev) goto done; err = -EINVAL; if (mreq->mr_alen > dev->addr_len) goto done; err = -ENOBUFS; i = kmalloc(sizeof(*i), GFP_KERNEL); if (i == NULL) goto done; err = 0; for (ml = po->mclist; ml; ml = ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { ml->count++; /* Free the new element ... */ kfree(i); goto done; } } i->type = mreq->mr_type; i->ifindex = mreq->mr_ifindex; i->alen = mreq->mr_alen; memcpy(i->addr, mreq->mr_address, i->alen); memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen); i->count = 1; i->next = po->mclist; po->mclist = i; err = packet_dev_mc(dev, i, 1); if (err) { po->mclist = i->next; kfree(i); } done: rtnl_unlock(); return err; } static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_mclist *ml, **mlp; rtnl_lock(); for (mlp = &pkt_sk(sk)->mclist; (ml = *mlp) != NULL; mlp = &ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { if (--ml->count == 0) { struct net_device *dev; *mlp = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev) packet_dev_mc(dev, ml, -1); kfree(ml); } break; } } rtnl_unlock(); return 0; } static void packet_flush_mclist(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml; if (!po->mclist) return; rtnl_lock(); while ((ml = po->mclist) != NULL) { struct net_device *dev; po->mclist = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev != NULL) packet_dev_mc(dev, ml, -1); kfree(ml); } rtnl_unlock(); } static int packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); int ret; if (level != SOL_PACKET) return -ENOPROTOOPT; switch (optname) { case PACKET_ADD_MEMBERSHIP: case PACKET_DROP_MEMBERSHIP: { struct packet_mreq_max mreq; int len = optlen; memset(&mreq, 0, sizeof(mreq)); if (len < sizeof(struct packet_mreq)) return -EINVAL; if (len > sizeof(mreq)) len = sizeof(mreq); if (copy_from_sockptr(&mreq, optval, len)) return -EFAULT; if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address))) return -EINVAL; if (optname == PACKET_ADD_MEMBERSHIP) ret = packet_mc_add(sk, &mreq); else ret = packet_mc_drop(sk, &mreq); return ret; } case PACKET_RX_RING: case PACKET_TX_RING: { union tpacket_req_u req_u; ret = -EINVAL; lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: if (optlen < sizeof(req_u.req)) break; ret = copy_from_sockptr(&req_u.req, optval, sizeof(req_u.req)) ? -EINVAL : 0; break; case TPACKET_V3: default: if (optlen < sizeof(req_u.req3)) break; ret = copy_from_sockptr(&req_u.req3, optval, sizeof(req_u.req3)) ? -EINVAL : 0; break; } if (!ret) ret = packet_set_ring(sk, &req_u, 0, optname == PACKET_TX_RING); release_sock(sk); return ret; } case PACKET_COPY_THRESH: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(pkt_sk(sk)->copy_thresh, val); return 0; } case PACKET_VERSION: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: break; default: return -EINVAL; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_version = val; ret = 0; } release_sock(sk); return ret; } case PACKET_RESERVE: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_reserve = val; ret = 0; } release_sock(sk); return ret; } case PACKET_LOSS: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { packet_sock_flag_set(po, PACKET_SOCK_TP_LOSS, val); ret = 0; } release_sock(sk); return ret; } case PACKET_AUXDATA: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_AUXDATA, val); return 0; } case PACKET_ORIGDEV: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_ORIGDEV, val); return 0; } case PACKET_VNET_HDR: case PACKET_VNET_HDR_SZ: { int val, hdr_len; if (sock->type != SOCK_RAW) return -EINVAL; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (optname == PACKET_VNET_HDR_SZ) { if (val && val != sizeof(struct virtio_net_hdr) && val != sizeof(struct virtio_net_hdr_mrg_rxbuf)) return -EINVAL; hdr_len = val; } else { hdr_len = val ? sizeof(struct virtio_net_hdr) : 0; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { WRITE_ONCE(po->vnet_hdr_sz, hdr_len); ret = 0; } release_sock(sk); return ret; } case PACKET_TIMESTAMP: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(po->tp_tstamp, val); return 0; } case PACKET_FANOUT: { struct fanout_args args = { 0 }; if (optlen != sizeof(int) && optlen != sizeof(args)) return -EINVAL; if (copy_from_sockptr(&args, optval, optlen)) return -EFAULT; return fanout_add(sk, &args); } case PACKET_FANOUT_DATA: { /* Paired with the WRITE_ONCE() in fanout_add() */ if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); } case PACKET_IGNORE_OUTGOING: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val < 0 || val > 1) return -EINVAL; WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec) packet_sock_flag_set(po, PACKET_SOCK_TX_HAS_OFF, val); release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_QDISC_BYPASS, val); return 0; } default: return -ENOPROTOOPT; } } static int packet_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { int len; int val, lv = sizeof(val); struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; int drops; if (level != SOL_PACKET) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case PACKET_STATISTICS: spin_lock_bh(&sk->sk_receive_queue.lock); memcpy(&st, &po->stats, sizeof(st)); memset(&po->stats, 0, sizeof(po->stats)); spin_unlock_bh(&sk->sk_receive_queue.lock); drops = atomic_xchg(&po->tp_drops, 0); if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); st.stats3.tp_drops = drops; st.stats3.tp_packets += drops; data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); st.stats1.tp_drops = drops; st.stats1.tp_packets += drops; data = &st.stats1; } break; case PACKET_AUXDATA: val = packet_sock_flag(po, PACKET_SOCK_AUXDATA); break; case PACKET_ORIGDEV: val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV); break; case PACKET_VNET_HDR: val = !!READ_ONCE(po->vnet_hdr_sz); break; case PACKET_VNET_HDR_SZ: val = READ_ONCE(po->vnet_hdr_sz); break; case PACKET_COPY_THRESH: val = READ_ONCE(pkt_sk(sk)->copy_thresh); break; case PACKET_VERSION: val = po->tp_version; break; case PACKET_HDRLEN: if (len > sizeof(int)) len = sizeof(int); if (len < sizeof(int)) return -EINVAL; if (copy_from_user(&val, optval, len)) return -EFAULT; switch (val) { case TPACKET_V1: val = sizeof(struct tpacket_hdr); break; case TPACKET_V2: val = sizeof(struct tpacket2_hdr); break; case TPACKET_V3: val = sizeof(struct tpacket3_hdr); break; default: return -EINVAL; } break; case PACKET_RESERVE: val = po->tp_reserve; break; case PACKET_LOSS: val = packet_sock_flag(po, PACKET_SOCK_TP_LOSS); break; case PACKET_TIMESTAMP: val = READ_ONCE(po->tp_tstamp); break; case PACKET_FANOUT: val = (po->fanout ? ((u32)po->fanout->id | ((u32)po->fanout->type << 16) | ((u32)po->fanout->flags << 24)) : 0); break; case PACKET_IGNORE_OUTGOING: val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) return -EINVAL; rstats.tp_all = atomic_long_read(&po->rollover->num); rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); data = &rstats; lv = sizeof(rstats); break; case PACKET_TX_HAS_OFF: val = packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF); break; case PACKET_QDISC_BYPASS: val = packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS); break; default: return -ENOPROTOOPT; } if (len > lv) len = lv; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, data, len)) return -EFAULT; return 0; } static int packet_notifier(struct notifier_block *this, unsigned long msg, void *ptr) { struct sock *sk; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); rcu_read_lock(); sk_for_each_rcu(sk, &net->packet.sklist) { struct packet_sock *po = pkt_sk(sk); switch (msg) { case NETDEV_UNREGISTER: if (po->mclist) packet_dev_mclist_delete(dev, &po->mclist); fallthrough; case NETDEV_DOWN: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); } break; case NETDEV_UP: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (po->num) register_prot_hook(sk); spin_unlock(&po->bind_lock); } break; } } rcu_read_unlock(); return NOTIFY_DONE; } static int packet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } #ifdef CONFIG_INET case SIOCADDRT: case SIOCDELRT: case SIOCDARP: case SIOCGARP: case SIOCSARP: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCSIFFLAGS: return inet_dgram_ops.ioctl(sock, cmd, arg); #endif default: return -ENOIOCTLCMD; } return 0; } static __poll_t packet_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); __poll_t mask = datagram_poll(file, sock, wait); spin_lock_bh(&sk->sk_receive_queue.lock); if (po->rx_ring.pg_vec) { if (!packet_previous_rx_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) mask |= EPOLLOUT | EPOLLWRNORM; } spin_unlock_bh(&sk->sk_write_queue.lock); return mask; } /* Dirty? Well, I still did not learn better way to account * for user mmaps. */ static void packet_mm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { .open = packet_mm_open, .close = packet_mm_close, }; static void free_pg_vec(struct pgv *pg_vec, unsigned int order, unsigned int len) { int i; for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { if (is_vmalloc_addr(pg_vec[i].buffer)) vfree(pg_vec[i].buffer); else free_pages((unsigned long)pg_vec[i].buffer, order); pg_vec[i].buffer = NULL; } } kfree(pg_vec); } static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* __get_free_pages failed, fall back to vmalloc */ buffer = vzalloc(array_size((1 << order), PAGE_SIZE)); if (buffer) return buffer; /* vmalloc failed, lets dig into swap here */ gfp_flags &= ~__GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* complete and utter failure */ return NULL; } static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) { unsigned int block_nr = req->tp_block_nr; struct pgv *pg_vec; int i; pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN); if (unlikely(!pg_vec)) goto out; for (i = 0; i < block_nr; i++) { pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } out: return pg_vec; out_free_pgvec: free_pg_vec(pg_vec, order, block_nr); pg_vec = NULL; goto out; } static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring) { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); unsigned long *rx_owner_map = NULL; int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; __be16 num; int err; /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; rb = tx_ring ? &po->tx_ring : &po->rx_ring; rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; err = -EBUSY; if (!closing) { if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; } if (req->tp_block_nr) { unsigned int min_frame_size; /* Sanity tests and some calculations */ err = -EBUSY; if (unlikely(rb->pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V1: po->tp_hdrlen = TPACKET_HDRLEN; break; case TPACKET_V2: po->tp_hdrlen = TPACKET2_HDRLEN; break; case TPACKET_V3: po->tp_hdrlen = TPACKET3_HDRLEN; break; } err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) goto out; if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; min_frame_size = po->tp_hdrlen + po->tp_reserve; if (po->tp_version >= TPACKET_V3 && req->tp_block_size < BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size) goto out; if (unlikely(req->tp_frame_size < min_frame_size)) goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) goto out; err = -ENOMEM; order = get_order(req->tp_block_size); pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V3: /* Block transmit is not supported yet */ if (!tx_ring) { init_prb_bdqc(po, rb, pg_vec, req_u); } else { struct tpacket_req3 *req3 = &req_u->req3; if (req3->tp_retire_blk_tov || req3->tp_sizeof_priv || req3->tp_feature_req_word) { err = -EINVAL; goto out_free_pg_vec; } } break; default: if (!tx_ring) { rx_owner_map = bitmap_alloc(req->tp_frame_nr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); if (!rx_owner_map) goto out_free_pg_vec; } break; } } /* Done */ else { err = -EINVAL; if (unlikely(req->tp_frame_nr)) goto out; } /* Detach socket from network */ spin_lock(&po->bind_lock); was_running = packet_sock_flag(po, PACKET_SOCK_RUNNING); num = po->num; if (was_running) { WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); synchronize_net(); err = -EBUSY; mutex_lock(&po->pg_vec_lock); if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); if (po->tp_version <= TPACKET_V2) swap(rb->rx_owner_map, rx_owner_map); rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; spin_unlock_bh(&rb_queue->lock); swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); if (atomic_long_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %ld\n", atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); if (was_running) { WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); if (pg_vec && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); } out_free_pg_vec: if (pg_vec) { bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); } out: return err; } static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); unsigned long size, expected_size; struct packet_ring_buffer *rb; unsigned long start; int err = -EINVAL; int i; if (vma->vm_pgoff) return -EINVAL; mutex_lock(&po->pg_vec_lock); expected_size = 0; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec) { expected_size += rb->pg_vec_len * rb->pg_vec_pages * PAGE_SIZE; } } if (expected_size == 0) goto out; size = vma->vm_end - vma->vm_start; if (size != expected_size) goto out; start = vma->vm_start; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec == NULL) continue; for (i = 0; i < rb->pg_vec_len; i++) { struct page *page; void *kaddr = rb->pg_vec[i].buffer; int pg_num; for (pg_num = 0; pg_num < rb->pg_vec_pages; pg_num++) { page = pgv_to_page(kaddr); err = vm_insert_page(vma, start, page); if (unlikely(err)) goto out; start += PAGE_SIZE; kaddr += PAGE_SIZE; } } } atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; out: mutex_unlock(&po->pg_vec_lock); return err; } static const struct proto_ops packet_ops_spkt = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind_spkt, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname_spkt, .poll = datagram_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = packet_sendmsg_spkt, .recvmsg = packet_recvmsg, .mmap = sock_no_mmap, }; static const struct proto_ops packet_ops = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname, .poll = packet_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = packet_setsockopt, .getsockopt = packet_getsockopt, .sendmsg = packet_sendmsg, .recvmsg = packet_recvmsg, .mmap = packet_mmap, }; static const struct net_proto_family packet_family_ops = { .family = PF_PACKET, .create = packet_create, .owner = THIS_MODULE, }; static struct notifier_block packet_netdev_notifier = { .notifier_call = packet_notifier, }; #ifdef CONFIG_PROC_FS static void *packet_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); rcu_read_lock(); return seq_hlist_start_head_rcu(&net->packet.sklist, *pos); } static void *packet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); return seq_hlist_next_rcu(v, &net->packet.sklist, pos); } static void packet_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int packet_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%*sRefCnt Type Proto Iface R Rmem User Inode\n", IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk"); else { struct sock *s = sk_entry(v); const struct packet_sock *po = pkt_sk(s); seq_printf(seq, "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, refcount_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), READ_ONCE(po->ifindex), packet_sock_flag(po, PACKET_SOCK_RUNNING), atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), sock_i_ino(s)); } return 0; } static const struct seq_operations packet_seq_ops = { .start = packet_seq_start, .next = packet_seq_next, .stop = packet_seq_stop, .show = packet_seq_show, }; #endif static int __net_init packet_net_init(struct net *net) { mutex_init(&net->packet.sklist_lock); INIT_HLIST_HEAD(&net->packet.sklist); #ifdef CONFIG_PROC_FS if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; #endif /* CONFIG_PROC_FS */ return 0; } static void __net_exit packet_net_exit(struct net *net) { remove_proc_entry("packet", net->proc_net); WARN_ON_ONCE(!hlist_empty(&net->packet.sklist)); } static struct pernet_operations packet_net_ops = { .init = packet_net_init, .exit = packet_net_exit, }; static void __exit packet_exit(void) { sock_unregister(PF_PACKET); proto_unregister(&packet_proto); unregister_netdevice_notifier(&packet_netdev_notifier); unregister_pernet_subsys(&packet_net_ops); } static int __init packet_init(void) { int rc; rc = register_pernet_subsys(&packet_net_ops); if (rc) goto out; rc = register_netdevice_notifier(&packet_netdev_notifier); if (rc) goto out_pernet; rc = proto_register(&packet_proto, 0); if (rc) goto out_notifier; rc = sock_register(&packet_family_ops); if (rc) goto out_proto; return 0; out_proto: proto_unregister(&packet_proto); out_notifier: unregister_netdevice_notifier(&packet_netdev_notifier); out_pernet: unregister_pernet_subsys(&packet_net_ops); out: return rc; } module_init(packet_init); module_exit(packet_exit); MODULE_DESCRIPTION("Packet socket support (AF_PACKET)"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_PACKET); |
| 39 39 31 31 4 29 4 29 2 30 2 30 31 31 1 31 2 6 33 33 3 5 33 33 33 33 33 23 7 23 1 23 23 11 26 26 26 2 24 1 23 23 61 61 61 1 59 3 3 3 62 28 20 28 61 24 24 220 62 61 39 39 24 39 2 2 1 1 129 30 30 119 119 24 34 52 37 2 26 7 24 24 34 34 71 67 46 103 96 103 103 6 2 3 4 1 127 127 115 31 27 8 197 182 121 6 6 6 6 6 6 1 6 6 23 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2003 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_shared.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_bmap.h" #include "xfs_quota.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_trans_space.h" #include "xfs_trans_priv.h" #include "xfs_qm.h" #include "xfs_trace.h" #include "xfs_log.h" #include "xfs_bmap_btree.h" #include "xfs_error.h" #include "xfs_health.h" /* * Lock order: * * ip->i_lock * qi->qi_tree_lock * dquot->q_qlock (xfs_dqlock() and friends) * dquot->q_flush (xfs_dqflock() and friends) * qi->qi_lru_lock * * If two dquots need to be locked the order is user before group/project, * otherwise by the lowest id first, see xfs_dqlock2. */ struct kmem_cache *xfs_dqtrx_cache; static struct kmem_cache *xfs_dquot_cache; static struct lock_class_key xfs_dquot_group_class; static struct lock_class_key xfs_dquot_project_class; /* Record observations of quota corruption with the health tracking system. */ static void xfs_dquot_mark_sick( struct xfs_dquot *dqp) { struct xfs_mount *mp = dqp->q_mount; switch (dqp->q_type) { case XFS_DQTYPE_USER: xfs_fs_mark_sick(mp, XFS_SICK_FS_UQUOTA); break; case XFS_DQTYPE_GROUP: xfs_fs_mark_sick(mp, XFS_SICK_FS_GQUOTA); break; case XFS_DQTYPE_PROJ: xfs_fs_mark_sick(mp, XFS_SICK_FS_PQUOTA); break; default: ASSERT(0); break; } } /* * This is called to free all the memory associated with a dquot */ void xfs_qm_dqdestroy( struct xfs_dquot *dqp) { ASSERT(list_empty(&dqp->q_lru)); kvfree(dqp->q_logitem.qli_item.li_lv_shadow); mutex_destroy(&dqp->q_qlock); XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot); kmem_cache_free(xfs_dquot_cache, dqp); } /* * If default limits are in force, push them into the dquot now. * We overwrite the dquot limits only if they are zero and this * is not the root dquot. */ void xfs_qm_adjust_dqlimits( struct xfs_dquot *dq) { struct xfs_mount *mp = dq->q_mount; struct xfs_quotainfo *q = mp->m_quotainfo; struct xfs_def_quota *defq; int prealloc = 0; ASSERT(dq->q_id); defq = xfs_get_defquota(q, xfs_dquot_type(dq)); if (!dq->q_blk.softlimit) { dq->q_blk.softlimit = defq->blk.soft; prealloc = 1; } if (!dq->q_blk.hardlimit) { dq->q_blk.hardlimit = defq->blk.hard; prealloc = 1; } if (!dq->q_ino.softlimit) dq->q_ino.softlimit = defq->ino.soft; if (!dq->q_ino.hardlimit) dq->q_ino.hardlimit = defq->ino.hard; if (!dq->q_rtb.softlimit) dq->q_rtb.softlimit = defq->rtb.soft; if (!dq->q_rtb.hardlimit) dq->q_rtb.hardlimit = defq->rtb.hard; if (prealloc) xfs_dquot_set_prealloc_limits(dq); } /* Set the expiration time of a quota's grace period. */ time64_t xfs_dquot_set_timeout( struct xfs_mount *mp, time64_t timeout) { struct xfs_quotainfo *qi = mp->m_quotainfo; return clamp_t(time64_t, timeout, qi->qi_expiry_min, qi->qi_expiry_max); } /* Set the length of the default grace period. */ time64_t xfs_dquot_set_grace_period( time64_t grace) { return clamp_t(time64_t, grace, XFS_DQ_GRACE_MIN, XFS_DQ_GRACE_MAX); } /* * Determine if this quota counter is over either limit and set the quota * timers as appropriate. */ static inline void xfs_qm_adjust_res_timer( struct xfs_mount *mp, struct xfs_dquot_res *res, struct xfs_quota_limits *qlim) { ASSERT(res->hardlimit == 0 || res->softlimit <= res->hardlimit); if ((res->softlimit && res->count > res->softlimit) || (res->hardlimit && res->count > res->hardlimit)) { if (res->timer == 0) res->timer = xfs_dquot_set_timeout(mp, ktime_get_real_seconds() + qlim->time); } else { res->timer = 0; } } /* * Check the limits and timers of a dquot and start or reset timers * if necessary. * This gets called even when quota enforcement is OFF, which makes our * life a little less complicated. (We just don't reject any quota * reservations in that case, when enforcement is off). * We also return 0 as the values of the timers in Q_GETQUOTA calls, when * enforcement's off. * In contrast, warnings are a little different in that they don't * 'automatically' get started when limits get exceeded. They do * get reset to zero, however, when we find the count to be under * the soft limit (they are only ever set non-zero via userspace). */ void xfs_qm_adjust_dqtimers( struct xfs_dquot *dq) { struct xfs_mount *mp = dq->q_mount; struct xfs_quotainfo *qi = mp->m_quotainfo; struct xfs_def_quota *defq; ASSERT(dq->q_id); defq = xfs_get_defquota(qi, xfs_dquot_type(dq)); xfs_qm_adjust_res_timer(dq->q_mount, &dq->q_blk, &defq->blk); xfs_qm_adjust_res_timer(dq->q_mount, &dq->q_ino, &defq->ino); xfs_qm_adjust_res_timer(dq->q_mount, &dq->q_rtb, &defq->rtb); } /* * initialize a buffer full of dquots and log the whole thing */ void xfs_qm_init_dquot_blk( struct xfs_trans *tp, xfs_dqid_t id, xfs_dqtype_t type, struct xfs_buf *bp) { struct xfs_mount *mp = tp->t_mountp; struct xfs_quotainfo *q = mp->m_quotainfo; struct xfs_dqblk *d; xfs_dqid_t curid; unsigned int qflag; unsigned int blftype; int i; ASSERT(tp); ASSERT(xfs_buf_islocked(bp)); switch (type) { case XFS_DQTYPE_USER: qflag = XFS_UQUOTA_CHKD; blftype = XFS_BLF_UDQUOT_BUF; break; case XFS_DQTYPE_PROJ: qflag = XFS_PQUOTA_CHKD; blftype = XFS_BLF_PDQUOT_BUF; break; case XFS_DQTYPE_GROUP: qflag = XFS_GQUOTA_CHKD; blftype = XFS_BLF_GDQUOT_BUF; break; default: ASSERT(0); return; } d = bp->b_addr; /* * ID of the first dquot in the block - id's are zero based. */ curid = id - (id % q->qi_dqperchunk); memset(d, 0, BBTOB(q->qi_dqchunklen)); for (i = 0; i < q->qi_dqperchunk; i++, d++, curid++) { d->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC); d->dd_diskdq.d_version = XFS_DQUOT_VERSION; d->dd_diskdq.d_id = cpu_to_be32(curid); d->dd_diskdq.d_type = type; if (curid > 0 && xfs_has_bigtime(mp)) d->dd_diskdq.d_type |= XFS_DQTYPE_BIGTIME; if (xfs_has_crc(mp)) { uuid_copy(&d->dd_uuid, &mp->m_sb.sb_meta_uuid); xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF); } } xfs_trans_dquot_buf(tp, bp, blftype); /* * quotacheck uses delayed writes to update all the dquots on disk in an * efficient manner instead of logging the individual dquot changes as * they are made. However if we log the buffer allocated here and crash * after quotacheck while the logged initialisation is still in the * active region of the log, log recovery can replay the dquot buffer * initialisation over the top of the checked dquots and corrupt quota * accounting. * * To avoid this problem, quotacheck cannot log the initialised buffer. * We must still dirty the buffer and write it back before the * allocation transaction clears the log. Therefore, mark the buffer as * ordered instead of logging it directly. This is safe for quotacheck * because it detects and repairs allocated but initialized dquot blocks * in the quota inodes. */ if (!(mp->m_qflags & qflag)) xfs_trans_ordered_buf(tp, bp); else xfs_trans_log_buf(tp, bp, 0, BBTOB(q->qi_dqchunklen) - 1); } /* * Initialize the dynamic speculative preallocation thresholds. The lo/hi * watermarks correspond to the soft and hard limits by default. If a soft limit * is not specified, we use 95% of the hard limit. */ void xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp) { uint64_t space; dqp->q_prealloc_hi_wmark = dqp->q_blk.hardlimit; dqp->q_prealloc_lo_wmark = dqp->q_blk.softlimit; if (!dqp->q_prealloc_lo_wmark) { dqp->q_prealloc_lo_wmark = dqp->q_prealloc_hi_wmark; do_div(dqp->q_prealloc_lo_wmark, 100); dqp->q_prealloc_lo_wmark *= 95; } space = dqp->q_prealloc_hi_wmark; do_div(space, 100); dqp->q_low_space[XFS_QLOWSP_1_PCNT] = space; dqp->q_low_space[XFS_QLOWSP_3_PCNT] = space * 3; dqp->q_low_space[XFS_QLOWSP_5_PCNT] = space * 5; } /* * Ensure that the given in-core dquot has a buffer on disk backing it, and * return the buffer locked and held. This is called when the bmapi finds a * hole. */ STATIC int xfs_dquot_disk_alloc( struct xfs_dquot *dqp, struct xfs_buf **bpp) { struct xfs_bmbt_irec map; struct xfs_trans *tp; struct xfs_mount *mp = dqp->q_mount; struct xfs_buf *bp; xfs_dqtype_t qtype = xfs_dquot_type(dqp); struct xfs_inode *quotip = xfs_quota_inode(mp, qtype); int nmaps = 1; int error; trace_xfs_dqalloc(dqp); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_dqalloc, XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp); if (error) return error; xfs_ilock(quotip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, quotip, 0); if (!xfs_this_quota_on(dqp->q_mount, qtype)) { /* * Return if this type of quotas is turned off while we didn't * have an inode lock */ error = -ESRCH; goto err_cancel; } error = xfs_iext_count_extend(tp, quotip, XFS_DATA_FORK, XFS_IEXT_ADD_NOSPLIT_CNT); if (error) goto err_cancel; /* Create the block mapping. */ error = xfs_bmapi_write(tp, quotip, dqp->q_fileoffset, XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA, 0, &map, &nmaps); if (error) goto err_cancel; ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB); ASSERT((map.br_startblock != DELAYSTARTBLOCK) && (map.br_startblock != HOLESTARTBLOCK)); /* * Keep track of the blkno to save a lookup later */ dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock); /* now we can just get the buffer (there's nothing to read yet) */ error = xfs_trans_get_buf(tp, mp->m_ddev_targp, dqp->q_blkno, mp->m_quotainfo->qi_dqchunklen, 0, &bp); if (error) goto err_cancel; bp->b_ops = &xfs_dquot_buf_ops; /* * Make a chunk of dquots out of this buffer and log * the entire thing. */ xfs_qm_init_dquot_blk(tp, dqp->q_id, qtype, bp); xfs_buf_set_ref(bp, XFS_DQUOT_REF); /* * Hold the buffer and join it to the dfops so that we'll still own * the buffer when we return to the caller. The buffer disposal on * error must be paid attention to very carefully, as it has been * broken since commit efa092f3d4c6 "[XFS] Fixes a bug in the quota * code when allocating a new dquot record" in 2005, and the later * conversion to xfs_defer_ops in commit 310a75a3c6c747 failed to keep * the buffer locked across the _defer_finish call. We can now do * this correctly with xfs_defer_bjoin. * * Above, we allocated a disk block for the dquot information and used * get_buf to initialize the dquot. If the _defer_finish fails, the old * transaction is gone but the new buffer is not joined or held to any * transaction, so we must _buf_relse it. * * If everything succeeds, the caller of this function is returned a * buffer that is locked and held to the transaction. The caller * is responsible for unlocking any buffer passed back, either * manually or by committing the transaction. On error, the buffer is * released and not passed back. * * Keep the quota inode ILOCKed until after the transaction commit to * maintain the atomicity of bmap/rmap updates. */ xfs_trans_bhold(tp, bp); error = xfs_trans_commit(tp); xfs_iunlock(quotip, XFS_ILOCK_EXCL); if (error) { xfs_buf_relse(bp); return error; } *bpp = bp; return 0; err_cancel: xfs_trans_cancel(tp); xfs_iunlock(quotip, XFS_ILOCK_EXCL); return error; } /* * Read in the in-core dquot's on-disk metadata and return the buffer. * Returns ENOENT to signal a hole. */ STATIC int xfs_dquot_disk_read( struct xfs_mount *mp, struct xfs_dquot *dqp, struct xfs_buf **bpp) { struct xfs_bmbt_irec map; struct xfs_buf *bp; xfs_dqtype_t qtype = xfs_dquot_type(dqp); struct xfs_inode *quotip = xfs_quota_inode(mp, qtype); uint lock_mode; int nmaps = 1; int error; lock_mode = xfs_ilock_data_map_shared(quotip); if (!xfs_this_quota_on(mp, qtype)) { /* * Return if this type of quotas is turned off while we * didn't have the quota inode lock. */ xfs_iunlock(quotip, lock_mode); return -ESRCH; } /* * Find the block map; no allocations yet */ error = xfs_bmapi_read(quotip, dqp->q_fileoffset, XFS_DQUOT_CLUSTER_SIZE_FSB, &map, &nmaps, 0); xfs_iunlock(quotip, lock_mode); if (error) return error; ASSERT(nmaps == 1); ASSERT(map.br_blockcount >= 1); ASSERT(map.br_startblock != DELAYSTARTBLOCK); if (map.br_startblock == HOLESTARTBLOCK) return -ENOENT; trace_xfs_dqtobp_read(dqp); /* * store the blkno etc so that we don't have to do the * mapping all the time */ dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock); error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno, mp->m_quotainfo->qi_dqchunklen, 0, &bp, &xfs_dquot_buf_ops); if (xfs_metadata_is_sick(error)) xfs_dquot_mark_sick(dqp); if (error) { ASSERT(bp == NULL); return error; } ASSERT(xfs_buf_islocked(bp)); xfs_buf_set_ref(bp, XFS_DQUOT_REF); *bpp = bp; return 0; } /* Allocate and initialize everything we need for an incore dquot. */ STATIC struct xfs_dquot * xfs_dquot_alloc( struct xfs_mount *mp, xfs_dqid_t id, xfs_dqtype_t type) { struct xfs_dquot *dqp; dqp = kmem_cache_zalloc(xfs_dquot_cache, GFP_KERNEL | __GFP_NOFAIL); dqp->q_type = type; dqp->q_id = id; dqp->q_mount = mp; INIT_LIST_HEAD(&dqp->q_lru); mutex_init(&dqp->q_qlock); init_waitqueue_head(&dqp->q_pinwait); dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk; /* * Offset of dquot in the (fixed sized) dquot chunk. */ dqp->q_bufoffset = (id % mp->m_quotainfo->qi_dqperchunk) * sizeof(struct xfs_dqblk); /* * Because we want to use a counting completion, complete * the flush completion once to allow a single access to * the flush completion without blocking. */ init_completion(&dqp->q_flush); complete(&dqp->q_flush); /* * Make sure group quotas have a different lock class than user * quotas. */ switch (type) { case XFS_DQTYPE_USER: /* uses the default lock class */ break; case XFS_DQTYPE_GROUP: lockdep_set_class(&dqp->q_qlock, &xfs_dquot_group_class); break; case XFS_DQTYPE_PROJ: lockdep_set_class(&dqp->q_qlock, &xfs_dquot_project_class); break; default: ASSERT(0); break; } xfs_qm_dquot_logitem_init(dqp); XFS_STATS_INC(mp, xs_qm_dquot); return dqp; } /* Check the ondisk dquot's id and type match what the incore dquot expects. */ static bool xfs_dquot_check_type( struct xfs_dquot *dqp, struct xfs_disk_dquot *ddqp) { uint8_t ddqp_type; uint8_t dqp_type; ddqp_type = ddqp->d_type & XFS_DQTYPE_REC_MASK; dqp_type = xfs_dquot_type(dqp); if (be32_to_cpu(ddqp->d_id) != dqp->q_id) return false; /* * V5 filesystems always expect an exact type match. V4 filesystems * expect an exact match for user dquots and for non-root group and * project dquots. */ if (xfs_has_crc(dqp->q_mount) || dqp_type == XFS_DQTYPE_USER || dqp->q_id != 0) return ddqp_type == dqp_type; /* * V4 filesystems support either group or project quotas, but not both * at the same time. The non-user quota file can be switched between * group and project quota uses depending on the mount options, which * means that we can encounter the other type when we try to load quota * defaults. Quotacheck will soon reset the entire quota file * (including the root dquot) anyway, but don't log scary corruption * reports to dmesg. */ return ddqp_type == XFS_DQTYPE_GROUP || ddqp_type == XFS_DQTYPE_PROJ; } /* Copy the in-core quota fields in from the on-disk buffer. */ STATIC int xfs_dquot_from_disk( struct xfs_dquot *dqp, struct xfs_buf *bp) { struct xfs_dqblk *dqb = xfs_buf_offset(bp, dqp->q_bufoffset); struct xfs_disk_dquot *ddqp = &dqb->dd_diskdq; /* * Ensure that we got the type and ID we were looking for. * Everything else was checked by the dquot buffer verifier. */ if (!xfs_dquot_check_type(dqp, ddqp)) { xfs_alert_tag(bp->b_mount, XFS_PTAG_VERIFIER_ERROR, "Metadata corruption detected at %pS, quota %u", __this_address, dqp->q_id); xfs_alert(bp->b_mount, "Unmount and run xfs_repair"); xfs_dquot_mark_sick(dqp); return -EFSCORRUPTED; } /* copy everything from disk dquot to the incore dquot */ dqp->q_type = ddqp->d_type; dqp->q_blk.hardlimit = be64_to_cpu(ddqp->d_blk_hardlimit); dqp->q_blk.softlimit = be64_to_cpu(ddqp->d_blk_softlimit); dqp->q_ino.hardlimit = be64_to_cpu(ddqp->d_ino_hardlimit); dqp->q_ino.softlimit = be64_to_cpu(ddqp->d_ino_softlimit); dqp->q_rtb.hardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit); dqp->q_rtb.softlimit = be64_to_cpu(ddqp->d_rtb_softlimit); dqp->q_blk.count = be64_to_cpu(ddqp->d_bcount); dqp->q_ino.count = be64_to_cpu(ddqp->d_icount); dqp->q_rtb.count = be64_to_cpu(ddqp->d_rtbcount); dqp->q_blk.timer = xfs_dquot_from_disk_ts(ddqp, ddqp->d_btimer); dqp->q_ino.timer = xfs_dquot_from_disk_ts(ddqp, ddqp->d_itimer); dqp->q_rtb.timer = xfs_dquot_from_disk_ts(ddqp, ddqp->d_rtbtimer); /* * Reservation counters are defined as reservation plus current usage * to avoid having to add every time. */ dqp->q_blk.reserved = dqp->q_blk.count; dqp->q_ino.reserved = dqp->q_ino.count; dqp->q_rtb.reserved = dqp->q_rtb.count; /* initialize the dquot speculative prealloc thresholds */ xfs_dquot_set_prealloc_limits(dqp); return 0; } /* Copy the in-core quota fields into the on-disk buffer. */ void xfs_dquot_to_disk( struct xfs_disk_dquot *ddqp, struct xfs_dquot *dqp) { ddqp->d_magic = cpu_to_be16(XFS_DQUOT_MAGIC); ddqp->d_version = XFS_DQUOT_VERSION; ddqp->d_type = dqp->q_type; ddqp->d_id = cpu_to_be32(dqp->q_id); ddqp->d_pad0 = 0; ddqp->d_pad = 0; ddqp->d_blk_hardlimit = cpu_to_be64(dqp->q_blk.hardlimit); ddqp->d_blk_softlimit = cpu_to_be64(dqp->q_blk.softlimit); ddqp->d_ino_hardlimit = cpu_to_be64(dqp->q_ino.hardlimit); ddqp->d_ino_softlimit = cpu_to_be64(dqp->q_ino.softlimit); ddqp->d_rtb_hardlimit = cpu_to_be64(dqp->q_rtb.hardlimit); ddqp->d_rtb_softlimit = cpu_to_be64(dqp->q_rtb.softlimit); ddqp->d_bcount = cpu_to_be64(dqp->q_blk.count); ddqp->d_icount = cpu_to_be64(dqp->q_ino.count); ddqp->d_rtbcount = cpu_to_be64(dqp->q_rtb.count); ddqp->d_bwarns = 0; ddqp->d_iwarns = 0; ddqp->d_rtbwarns = 0; ddqp->d_btimer = xfs_dquot_to_disk_ts(dqp, dqp->q_blk.timer); ddqp->d_itimer = xfs_dquot_to_disk_ts(dqp, dqp->q_ino.timer); ddqp->d_rtbtimer = xfs_dquot_to_disk_ts(dqp, dqp->q_rtb.timer); } /* * Read in the ondisk dquot using dqtobp() then copy it to an incore version, * and release the buffer immediately. If @can_alloc is true, fill any * holes in the on-disk metadata. */ static int xfs_qm_dqread( struct xfs_mount *mp, xfs_dqid_t id, xfs_dqtype_t type, bool can_alloc, struct xfs_dquot **dqpp) { struct xfs_dquot *dqp; struct xfs_buf *bp; int error; dqp = xfs_dquot_alloc(mp, id, type); trace_xfs_dqread(dqp); /* Try to read the buffer, allocating if necessary. */ error = xfs_dquot_disk_read(mp, dqp, &bp); if (error == -ENOENT && can_alloc) error = xfs_dquot_disk_alloc(dqp, &bp); if (error) goto err; /* * At this point we should have a clean locked buffer. Copy the data * to the incore dquot and release the buffer since the incore dquot * has its own locking protocol so we needn't tie up the buffer any * further. */ ASSERT(xfs_buf_islocked(bp)); error = xfs_dquot_from_disk(dqp, bp); xfs_buf_relse(bp); if (error) goto err; *dqpp = dqp; return error; err: trace_xfs_dqread_fail(dqp); xfs_qm_dqdestroy(dqp); *dqpp = NULL; return error; } /* * Advance to the next id in the current chunk, or if at the * end of the chunk, skip ahead to first id in next allocated chunk * using the SEEK_DATA interface. */ static int xfs_dq_get_next_id( struct xfs_mount *mp, xfs_dqtype_t type, xfs_dqid_t *id) { struct xfs_inode *quotip = xfs_quota_inode(mp, type); xfs_dqid_t next_id = *id + 1; /* simple advance */ uint lock_flags; struct xfs_bmbt_irec got; struct xfs_iext_cursor cur; xfs_fsblock_t start; int error = 0; /* If we'd wrap past the max ID, stop */ if (next_id < *id) return -ENOENT; /* If new ID is within the current chunk, advancing it sufficed */ if (next_id % mp->m_quotainfo->qi_dqperchunk) { *id = next_id; return 0; } /* Nope, next_id is now past the current chunk, so find the next one */ start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk; lock_flags = xfs_ilock_data_map_shared(quotip); error = xfs_iread_extents(NULL, quotip, XFS_DATA_FORK); if (error) return error; if (xfs_iext_lookup_extent(quotip, "ip->i_df, start, &cur, &got)) { /* contiguous chunk, bump startoff for the id calculation */ if (got.br_startoff < start) got.br_startoff = start; *id = got.br_startoff * mp->m_quotainfo->qi_dqperchunk; } else { error = -ENOENT; } xfs_iunlock(quotip, lock_flags); return error; } /* * Look up the dquot in the in-core cache. If found, the dquot is returned * locked and ready to go. */ static struct xfs_dquot * xfs_qm_dqget_cache_lookup( struct xfs_mount *mp, struct xfs_quotainfo *qi, struct radix_tree_root *tree, xfs_dqid_t id) { struct xfs_dquot *dqp; restart: mutex_lock(&qi->qi_tree_lock); dqp = radix_tree_lookup(tree, id); if (!dqp) { mutex_unlock(&qi->qi_tree_lock); XFS_STATS_INC(mp, xs_qm_dqcachemisses); return NULL; } xfs_dqlock(dqp); if (dqp->q_flags & XFS_DQFLAG_FREEING) { xfs_dqunlock(dqp); mutex_unlock(&qi->qi_tree_lock); trace_xfs_dqget_freeing(dqp); delay(1); goto restart; } dqp->q_nrefs++; mutex_unlock(&qi->qi_tree_lock); trace_xfs_dqget_hit(dqp); XFS_STATS_INC(mp, xs_qm_dqcachehits); return dqp; } /* * Try to insert a new dquot into the in-core cache. If an error occurs the * caller should throw away the dquot and start over. Otherwise, the dquot * is returned locked (and held by the cache) as if there had been a cache * hit. * * The insert needs to be done under memalloc_nofs context because the radix * tree can do memory allocation during insert. The qi->qi_tree_lock is taken in * memory reclaim when freeing unused dquots, so we cannot have the radix tree * node allocation recursing into filesystem reclaim whilst we hold the * qi_tree_lock. */ static int xfs_qm_dqget_cache_insert( struct xfs_mount *mp, struct xfs_quotainfo *qi, struct radix_tree_root *tree, xfs_dqid_t id, struct xfs_dquot *dqp) { unsigned int nofs_flags; int error; nofs_flags = memalloc_nofs_save(); mutex_lock(&qi->qi_tree_lock); error = radix_tree_insert(tree, id, dqp); if (unlikely(error)) { /* Duplicate found! Caller must try again. */ trace_xfs_dqget_dup(dqp); goto out_unlock; } /* Return a locked dquot to the caller, with a reference taken. */ xfs_dqlock(dqp); dqp->q_nrefs = 1; qi->qi_dquots++; out_unlock: mutex_unlock(&qi->qi_tree_lock); memalloc_nofs_restore(nofs_flags); return error; } /* Check our input parameters. */ static int xfs_qm_dqget_checks( struct xfs_mount *mp, xfs_dqtype_t type) { switch (type) { case XFS_DQTYPE_USER: if (!XFS_IS_UQUOTA_ON(mp)) return -ESRCH; return 0; case XFS_DQTYPE_GROUP: if (!XFS_IS_GQUOTA_ON(mp)) return -ESRCH; return 0; case XFS_DQTYPE_PROJ: if (!XFS_IS_PQUOTA_ON(mp)) return -ESRCH; return 0; default: WARN_ON_ONCE(0); return -EINVAL; } } /* * Given the file system, id, and type (UDQUOT/GDQUOT/PDQUOT), return a * locked dquot, doing an allocation (if requested) as needed. */ int xfs_qm_dqget( struct xfs_mount *mp, xfs_dqid_t id, xfs_dqtype_t type, bool can_alloc, struct xfs_dquot **O_dqpp) { struct xfs_quotainfo *qi = mp->m_quotainfo; struct radix_tree_root *tree = xfs_dquot_tree(qi, type); struct xfs_dquot *dqp; int error; error = xfs_qm_dqget_checks(mp, type); if (error) return error; restart: dqp = xfs_qm_dqget_cache_lookup(mp, qi, tree, id); if (dqp) { *O_dqpp = dqp; return 0; } error = xfs_qm_dqread(mp, id, type, can_alloc, &dqp); if (error) return error; error = xfs_qm_dqget_cache_insert(mp, qi, tree, id, dqp); if (error) { /* * Duplicate found. Just throw away the new dquot and start * over. */ xfs_qm_dqdestroy(dqp); XFS_STATS_INC(mp, xs_qm_dquot_dups); goto restart; } trace_xfs_dqget_miss(dqp); *O_dqpp = dqp; return 0; } /* * Given a dquot id and type, read and initialize a dquot from the on-disk * metadata. This function is only for use during quota initialization so * it ignores the dquot cache assuming that the dquot shrinker isn't set up. * The caller is responsible for _qm_dqdestroy'ing the returned dquot. */ int xfs_qm_dqget_uncached( struct xfs_mount *mp, xfs_dqid_t id, xfs_dqtype_t type, struct xfs_dquot **dqpp) { int error; error = xfs_qm_dqget_checks(mp, type); if (error) return error; return xfs_qm_dqread(mp, id, type, 0, dqpp); } /* Return the quota id for a given inode and type. */ xfs_dqid_t xfs_qm_id_for_quotatype( struct xfs_inode *ip, xfs_dqtype_t type) { switch (type) { case XFS_DQTYPE_USER: return i_uid_read(VFS_I(ip)); case XFS_DQTYPE_GROUP: return i_gid_read(VFS_I(ip)); case XFS_DQTYPE_PROJ: return ip->i_projid; } ASSERT(0); return 0; } /* * Return the dquot for a given inode and type. If @can_alloc is true, then * allocate blocks if needed. The inode's ILOCK must be held and it must not * have already had an inode attached. */ int xfs_qm_dqget_inode( struct xfs_inode *ip, xfs_dqtype_t type, bool can_alloc, struct xfs_dquot **O_dqpp) { struct xfs_mount *mp = ip->i_mount; struct xfs_quotainfo *qi = mp->m_quotainfo; struct radix_tree_root *tree = xfs_dquot_tree(qi, type); struct xfs_dquot *dqp; xfs_dqid_t id; int error; error = xfs_qm_dqget_checks(mp, type); if (error) return error; xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); ASSERT(xfs_inode_dquot(ip, type) == NULL); id = xfs_qm_id_for_quotatype(ip, type); restart: dqp = xfs_qm_dqget_cache_lookup(mp, qi, tree, id); if (dqp) { *O_dqpp = dqp; return 0; } /* * Dquot cache miss. We don't want to keep the inode lock across * a (potential) disk read. Also we don't want to deal with the lock * ordering between quotainode and this inode. OTOH, dropping the inode * lock here means dealing with a chown that can happen before * we re-acquire the lock. */ xfs_iunlock(ip, XFS_ILOCK_EXCL); error = xfs_qm_dqread(mp, id, type, can_alloc, &dqp); xfs_ilock(ip, XFS_ILOCK_EXCL); if (error) return error; /* * A dquot could be attached to this inode by now, since we had * dropped the ilock. */ if (xfs_this_quota_on(mp, type)) { struct xfs_dquot *dqp1; dqp1 = xfs_inode_dquot(ip, type); if (dqp1) { xfs_qm_dqdestroy(dqp); dqp = dqp1; xfs_dqlock(dqp); goto dqret; } } else { /* inode stays locked on return */ xfs_qm_dqdestroy(dqp); return -ESRCH; } error = xfs_qm_dqget_cache_insert(mp, qi, tree, id, dqp); if (error) { /* * Duplicate found. Just throw away the new dquot and start * over. */ xfs_qm_dqdestroy(dqp); XFS_STATS_INC(mp, xs_qm_dquot_dups); goto restart; } dqret: xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); trace_xfs_dqget_miss(dqp); *O_dqpp = dqp; return 0; } /* * Starting at @id and progressing upwards, look for an initialized incore * dquot, lock it, and return it. */ int xfs_qm_dqget_next( struct xfs_mount *mp, xfs_dqid_t id, xfs_dqtype_t type, struct xfs_dquot **dqpp) { struct xfs_dquot *dqp; int error = 0; *dqpp = NULL; for (; !error; error = xfs_dq_get_next_id(mp, type, &id)) { error = xfs_qm_dqget(mp, id, type, false, &dqp); if (error == -ENOENT) continue; else if (error != 0) break; if (!XFS_IS_DQUOT_UNINITIALIZED(dqp)) { *dqpp = dqp; return 0; } xfs_qm_dqput(dqp); } return error; } /* * Release a reference to the dquot (decrement ref-count) and unlock it. * * If there is a group quota attached to this dquot, carefully release that * too without tripping over deadlocks'n'stuff. */ void xfs_qm_dqput( struct xfs_dquot *dqp) { ASSERT(dqp->q_nrefs > 0); ASSERT(XFS_DQ_IS_LOCKED(dqp)); trace_xfs_dqput(dqp); if (--dqp->q_nrefs == 0) { struct xfs_quotainfo *qi = dqp->q_mount->m_quotainfo; trace_xfs_dqput_free(dqp); if (list_lru_add_obj(&qi->qi_lru, &dqp->q_lru)) XFS_STATS_INC(dqp->q_mount, xs_qm_dquot_unused); } xfs_dqunlock(dqp); } /* * Release a dquot. Flush it if dirty, then dqput() it. * dquot must not be locked. */ void xfs_qm_dqrele( struct xfs_dquot *dqp) { if (!dqp) return; trace_xfs_dqrele(dqp); xfs_dqlock(dqp); /* * We don't care to flush it if the dquot is dirty here. * That will create stutters that we want to avoid. * Instead we do a delayed write when we try to reclaim * a dirty dquot. Also xfs_sync will take part of the burden... */ xfs_qm_dqput(dqp); } /* * This is the dquot flushing I/O completion routine. It is called * from interrupt level when the buffer containing the dquot is * flushed to disk. It is responsible for removing the dquot logitem * from the AIL if it has not been re-logged, and unlocking the dquot's * flush lock. This behavior is very similar to that of inodes.. */ static void xfs_qm_dqflush_done( struct xfs_log_item *lip) { struct xfs_dq_logitem *qip = (struct xfs_dq_logitem *)lip; struct xfs_dquot *dqp = qip->qli_dquot; struct xfs_ail *ailp = lip->li_ailp; xfs_lsn_t tail_lsn; /* * We only want to pull the item from the AIL if its * location in the log has not changed since we started the flush. * Thus, we only bother if the dquot's lsn has * not changed. First we check the lsn outside the lock * since it's cheaper, and then we recheck while * holding the lock before removing the dquot from the AIL. */ if (test_bit(XFS_LI_IN_AIL, &lip->li_flags) && ((lip->li_lsn == qip->qli_flush_lsn) || test_bit(XFS_LI_FAILED, &lip->li_flags))) { spin_lock(&ailp->ail_lock); xfs_clear_li_failed(lip); if (lip->li_lsn == qip->qli_flush_lsn) { /* xfs_ail_update_finish() drops the AIL lock */ tail_lsn = xfs_ail_delete_one(ailp, lip); xfs_ail_update_finish(ailp, tail_lsn); } else { spin_unlock(&ailp->ail_lock); } } /* * Release the dq's flush lock since we're done with it. */ xfs_dqfunlock(dqp); } void xfs_buf_dquot_iodone( struct xfs_buf *bp) { struct xfs_log_item *lip, *n; list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) { list_del_init(&lip->li_bio_list); xfs_qm_dqflush_done(lip); } } void xfs_buf_dquot_io_fail( struct xfs_buf *bp) { struct xfs_log_item *lip; spin_lock(&bp->b_mount->m_ail->ail_lock); list_for_each_entry(lip, &bp->b_li_list, li_bio_list) xfs_set_li_failed(lip, bp); spin_unlock(&bp->b_mount->m_ail->ail_lock); } /* Check incore dquot for errors before we flush. */ static xfs_failaddr_t xfs_qm_dqflush_check( struct xfs_dquot *dqp) { xfs_dqtype_t type = xfs_dquot_type(dqp); if (type != XFS_DQTYPE_USER && type != XFS_DQTYPE_GROUP && type != XFS_DQTYPE_PROJ) return __this_address; if (dqp->q_id == 0) return NULL; if (dqp->q_blk.softlimit && dqp->q_blk.count > dqp->q_blk.softlimit && !dqp->q_blk.timer) return __this_address; if (dqp->q_ino.softlimit && dqp->q_ino.count > dqp->q_ino.softlimit && !dqp->q_ino.timer) return __this_address; if (dqp->q_rtb.softlimit && dqp->q_rtb.count > dqp->q_rtb.softlimit && !dqp->q_rtb.timer) return __this_address; /* bigtime flag should never be set on root dquots */ if (dqp->q_type & XFS_DQTYPE_BIGTIME) { if (!xfs_has_bigtime(dqp->q_mount)) return __this_address; if (dqp->q_id == 0) return __this_address; } return NULL; } /* * Write a modified dquot to disk. * The dquot must be locked and the flush lock too taken by caller. * The flush lock will not be unlocked until the dquot reaches the disk, * but the dquot is free to be unlocked and modified by the caller * in the interim. Dquot is still locked on return. This behavior is * identical to that of inodes. */ int xfs_qm_dqflush( struct xfs_dquot *dqp, struct xfs_buf **bpp) { struct xfs_mount *mp = dqp->q_mount; struct xfs_log_item *lip = &dqp->q_logitem.qli_item; struct xfs_buf *bp; struct xfs_dqblk *dqblk; xfs_failaddr_t fa; int error; ASSERT(XFS_DQ_IS_LOCKED(dqp)); ASSERT(!completion_done(&dqp->q_flush)); trace_xfs_dqflush(dqp); *bpp = NULL; xfs_qm_dqunpin_wait(dqp); /* * Get the buffer containing the on-disk dquot */ error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno, mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK, &bp, &xfs_dquot_buf_ops); if (error == -EAGAIN) goto out_unlock; if (xfs_metadata_is_sick(error)) xfs_dquot_mark_sick(dqp); if (error) goto out_abort; fa = xfs_qm_dqflush_check(dqp); if (fa) { xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS", dqp->q_id, fa); xfs_buf_relse(bp); xfs_dquot_mark_sick(dqp); error = -EFSCORRUPTED; goto out_abort; } /* Flush the incore dquot to the ondisk buffer. */ dqblk = xfs_buf_offset(bp, dqp->q_bufoffset); xfs_dquot_to_disk(&dqblk->dd_diskdq, dqp); /* * Clear the dirty field and remember the flush lsn for later use. */ dqp->q_flags &= ~XFS_DQFLAG_DIRTY; xfs_trans_ail_copy_lsn(mp->m_ail, &dqp->q_logitem.qli_flush_lsn, &dqp->q_logitem.qli_item.li_lsn); /* * copy the lsn into the on-disk dquot now while we have the in memory * dquot here. This can't be done later in the write verifier as we * can't get access to the log item at that point in time. * * We also calculate the CRC here so that the on-disk dquot in the * buffer always has a valid CRC. This ensures there is no possibility * of a dquot without an up-to-date CRC getting to disk. */ if (xfs_has_crc(mp)) { dqblk->dd_lsn = cpu_to_be64(dqp->q_logitem.qli_item.li_lsn); xfs_update_cksum((char *)dqblk, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF); } /* * Attach the dquot to the buffer so that we can remove this dquot from * the AIL and release the flush lock once the dquot is synced to disk. */ bp->b_flags |= _XBF_DQUOTS; list_add_tail(&dqp->q_logitem.qli_item.li_bio_list, &bp->b_li_list); /* * If the buffer is pinned then push on the log so we won't * get stuck waiting in the write for too long. */ if (xfs_buf_ispinned(bp)) { trace_xfs_dqflush_force(dqp); xfs_log_force(mp, 0); } trace_xfs_dqflush_done(dqp); *bpp = bp; return 0; out_abort: dqp->q_flags &= ~XFS_DQFLAG_DIRTY; xfs_trans_ail_delete(lip, 0); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); out_unlock: xfs_dqfunlock(dqp); return error; } /* * Lock two xfs_dquot structures. * * To avoid deadlocks we always lock the quota structure with * the lowerd id first. */ void xfs_dqlock2( struct xfs_dquot *d1, struct xfs_dquot *d2) { if (d1 && d2) { ASSERT(d1 != d2); if (d1->q_id > d2->q_id) { mutex_lock(&d2->q_qlock); mutex_lock_nested(&d1->q_qlock, XFS_QLOCK_NESTED); } else { mutex_lock(&d1->q_qlock); mutex_lock_nested(&d2->q_qlock, XFS_QLOCK_NESTED); } } else if (d1) { mutex_lock(&d1->q_qlock); } else if (d2) { mutex_lock(&d2->q_qlock); } } static int xfs_dqtrx_cmp( const void *a, const void *b) { const struct xfs_dqtrx *qa = a; const struct xfs_dqtrx *qb = b; if (qa->qt_dquot->q_id > qb->qt_dquot->q_id) return 1; if (qa->qt_dquot->q_id < qb->qt_dquot->q_id) return -1; return 0; } void xfs_dqlockn( struct xfs_dqtrx *q) { unsigned int i; BUILD_BUG_ON(XFS_QM_TRANS_MAXDQS > MAX_LOCKDEP_SUBCLASSES); /* Sort in order of dquot id, do not allow duplicates */ for (i = 0; i < XFS_QM_TRANS_MAXDQS && q[i].qt_dquot != NULL; i++) { unsigned int j; for (j = 0; j < i; j++) ASSERT(q[i].qt_dquot != q[j].qt_dquot); } if (i == 0) return; sort(q, i, sizeof(struct xfs_dqtrx), xfs_dqtrx_cmp, NULL); mutex_lock(&q[0].qt_dquot->q_qlock); for (i = 1; i < XFS_QM_TRANS_MAXDQS && q[i].qt_dquot != NULL; i++) mutex_lock_nested(&q[i].qt_dquot->q_qlock, XFS_QLOCK_NESTED + i - 1); } int __init xfs_qm_init(void) { xfs_dquot_cache = kmem_cache_create("xfs_dquot", sizeof(struct xfs_dquot), 0, 0, NULL); if (!xfs_dquot_cache) goto out; xfs_dqtrx_cache = kmem_cache_create("xfs_dqtrx", sizeof(struct xfs_dquot_acct), 0, 0, NULL); if (!xfs_dqtrx_cache) goto out_free_dquot_cache; return 0; out_free_dquot_cache: kmem_cache_destroy(xfs_dquot_cache); out: return -ENOMEM; } void xfs_qm_exit(void) { kmem_cache_destroy(xfs_dqtrx_cache); kmem_cache_destroy(xfs_dquot_cache); } |
| 132 132 132 132 496 496 295 456 204 204 494 388 16 338 100 305 391 203 9 462 492 7 2 495 109 460 495 16 23 492 100 313 2 162 116 63 102 4 4 4 4 4 4 4 4 4 4 4 494 494 4 405 337 496 2 496 156 492 494 4 479 478 479 465 473 194 195 195 93 82 11 93 353 323 338 164 144 441 199 350 426 443 443 441 441 325 5 359 22 440 4 64 406 27 27 441 172 172 172 117 63 204 204 1 203 233 233 8 230 134 5 130 69 47 23 44 42 2 2 42 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. * Copyright (C) 2010 Red Hat, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_extent_busy.h" #include "xfs_quota.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_trace.h" #include "xfs_error.h" #include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_dquot_item.h" #include "xfs_dquot.h" #include "xfs_icache.h" #include "xfs_rtbitmap.h" struct kmem_cache *xfs_trans_cache; #if defined(CONFIG_TRACEPOINTS) static void xfs_trans_trace_reservations( struct xfs_mount *mp) { struct xfs_trans_res *res; struct xfs_trans_res *end_res; int i; res = (struct xfs_trans_res *)M_RES(mp); end_res = (struct xfs_trans_res *)(M_RES(mp) + 1); for (i = 0; res < end_res; i++, res++) trace_xfs_trans_resv_calc(mp, i, res); } #else # define xfs_trans_trace_reservations(mp) #endif /* * Initialize the precomputed transaction reservation values * in the mount structure. */ void xfs_trans_init( struct xfs_mount *mp) { xfs_trans_resv_calc(mp, M_RES(mp)); xfs_trans_trace_reservations(mp); } /* * Free the transaction structure. If there is more clean up * to do when the structure is freed, add it here. */ STATIC void xfs_trans_free( struct xfs_trans *tp) { xfs_extent_busy_sort(&tp->t_busy); xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false); trace_xfs_trans_free(tp, _RET_IP_); xfs_trans_clear_context(tp); if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT)) sb_end_intwrite(tp->t_mountp->m_super); xfs_trans_free_dqinfo(tp); kmem_cache_free(xfs_trans_cache, tp); } /* * This is called to create a new transaction which will share the * permanent log reservation of the given transaction. The remaining * unused block and rt extent reservations are also inherited. This * implies that the original transaction is no longer allowed to allocate * blocks. Locks and log items, however, are no inherited. They must * be added to the new transaction explicitly. */ STATIC struct xfs_trans * xfs_trans_dup( struct xfs_trans *tp) { struct xfs_trans *ntp; trace_xfs_trans_dup(tp, _RET_IP_); ntp = kmem_cache_zalloc(xfs_trans_cache, GFP_KERNEL | __GFP_NOFAIL); /* * Initialize the new transaction structure. */ ntp->t_magic = XFS_TRANS_HEADER_MAGIC; ntp->t_mountp = tp->t_mountp; INIT_LIST_HEAD(&ntp->t_items); INIT_LIST_HEAD(&ntp->t_busy); INIT_LIST_HEAD(&ntp->t_dfops); ntp->t_highest_agno = NULLAGNUMBER; ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); ASSERT(tp->t_ticket != NULL); ntp->t_flags = XFS_TRANS_PERM_LOG_RES | (tp->t_flags & XFS_TRANS_RESERVE) | (tp->t_flags & XFS_TRANS_NO_WRITECOUNT) | (tp->t_flags & XFS_TRANS_RES_FDBLKS); /* We gave our writer reference to the new transaction */ tp->t_flags |= XFS_TRANS_NO_WRITECOUNT; ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket); ASSERT(tp->t_blk_res >= tp->t_blk_res_used); ntp->t_blk_res = tp->t_blk_res - tp->t_blk_res_used; tp->t_blk_res = tp->t_blk_res_used; ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used; tp->t_rtx_res = tp->t_rtx_res_used; xfs_trans_switch_context(tp, ntp); /* move deferred ops over to the new tp */ xfs_defer_move(ntp, tp); xfs_trans_dup_dqinfo(tp, ntp); return ntp; } /* * This is called to reserve free disk blocks and log space for the * given transaction. This must be done before allocating any resources * within the transaction. * * This will return ENOSPC if there are not enough blocks available. * It will sleep waiting for available log space. * The only valid value for the flags parameter is XFS_RES_LOG_PERM, which * is used by long running transactions. If any one of the reservations * fails then they will all be backed out. * * This does not do quota reservations. That typically is done by the * caller afterwards. */ static int xfs_trans_reserve( struct xfs_trans *tp, struct xfs_trans_res *resp, uint blocks, uint rtextents) { struct xfs_mount *mp = tp->t_mountp; int error = 0; bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0; /* * Attempt to reserve the needed disk blocks by decrementing * the number needed from the number available. This will * fail if the count would go below zero. */ if (blocks > 0) { error = xfs_dec_fdblocks(mp, blocks, rsvd); if (error != 0) return -ENOSPC; tp->t_blk_res += blocks; } /* * Reserve the log space needed for this transaction. */ if (resp->tr_logres > 0) { bool permanent = false; ASSERT(tp->t_log_res == 0 || tp->t_log_res == resp->tr_logres); ASSERT(tp->t_log_count == 0 || tp->t_log_count == resp->tr_logcount); if (resp->tr_logflags & XFS_TRANS_PERM_LOG_RES) { tp->t_flags |= XFS_TRANS_PERM_LOG_RES; permanent = true; } else { ASSERT(tp->t_ticket == NULL); ASSERT(!(tp->t_flags & XFS_TRANS_PERM_LOG_RES)); } if (tp->t_ticket != NULL) { ASSERT(resp->tr_logflags & XFS_TRANS_PERM_LOG_RES); error = xfs_log_regrant(mp, tp->t_ticket); } else { error = xfs_log_reserve(mp, resp->tr_logres, resp->tr_logcount, &tp->t_ticket, permanent); } if (error) goto undo_blocks; tp->t_log_res = resp->tr_logres; tp->t_log_count = resp->tr_logcount; } /* * Attempt to reserve the needed realtime extents by decrementing * the number needed from the number available. This will * fail if the count would go below zero. */ if (rtextents > 0) { error = xfs_dec_frextents(mp, rtextents); if (error) { error = -ENOSPC; goto undo_log; } tp->t_rtx_res += rtextents; } return 0; /* * Error cases jump to one of these labels to undo any * reservations which have already been performed. */ undo_log: if (resp->tr_logres > 0) { xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket); tp->t_ticket = NULL; tp->t_log_res = 0; tp->t_flags &= ~XFS_TRANS_PERM_LOG_RES; } undo_blocks: if (blocks > 0) { xfs_add_fdblocks(mp, blocks); tp->t_blk_res = 0; } return error; } int xfs_trans_alloc( struct xfs_mount *mp, struct xfs_trans_res *resp, uint blocks, uint rtextents, uint flags, struct xfs_trans **tpp) { struct xfs_trans *tp; bool want_retry = true; int error; /* * Allocate the handle before we do our freeze accounting and setting up * GFP_NOFS allocation context so that we avoid lockdep false positives * by doing GFP_KERNEL allocations inside sb_start_intwrite(). */ retry: tp = kmem_cache_zalloc(xfs_trans_cache, GFP_KERNEL | __GFP_NOFAIL); if (!(flags & XFS_TRANS_NO_WRITECOUNT)) sb_start_intwrite(mp->m_super); xfs_trans_set_context(tp); /* * Zero-reservation ("empty") transactions can't modify anything, so * they're allowed to run while we're frozen. */ WARN_ON(resp->tr_logres > 0 && mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE); ASSERT(!(flags & XFS_TRANS_RES_FDBLKS) || xfs_has_lazysbcount(mp)); tp->t_magic = XFS_TRANS_HEADER_MAGIC; tp->t_flags = flags; tp->t_mountp = mp; INIT_LIST_HEAD(&tp->t_items); INIT_LIST_HEAD(&tp->t_busy); INIT_LIST_HEAD(&tp->t_dfops); tp->t_highest_agno = NULLAGNUMBER; error = xfs_trans_reserve(tp, resp, blocks, rtextents); if (error == -ENOSPC && want_retry) { xfs_trans_cancel(tp); /* * We weren't able to reserve enough space for the transaction. * Flush the other speculative space allocations to free space. * Do not perform a synchronous scan because callers can hold * other locks. */ error = xfs_blockgc_flush_all(mp); if (error) return error; want_retry = false; goto retry; } if (error) { xfs_trans_cancel(tp); return error; } trace_xfs_trans_alloc(tp, _RET_IP_); *tpp = tp; return 0; } /* * Create an empty transaction with no reservation. This is a defensive * mechanism for routines that query metadata without actually modifying them -- * if the metadata being queried is somehow cross-linked (think a btree block * pointer that points higher in the tree), we risk deadlock. However, blocks * grabbed as part of a transaction can be re-grabbed. The verifiers will * notice the corrupt block and the operation will fail back to userspace * without deadlocking. * * Note the zero-length reservation; this transaction MUST be cancelled without * any dirty data. * * Callers should obtain freeze protection to avoid a conflict with fs freezing * where we can be grabbing buffers at the same time that freeze is trying to * drain the buffer LRU list. */ int xfs_trans_alloc_empty( struct xfs_mount *mp, struct xfs_trans **tpp) { struct xfs_trans_res resv = {0}; return xfs_trans_alloc(mp, &resv, 0, 0, XFS_TRANS_NO_WRITECOUNT, tpp); } /* * Record the indicated change to the given field for application * to the file system's superblock when the transaction commits. * For now, just store the change in the transaction structure. * * Mark the transaction structure to indicate that the superblock * needs to be updated before committing. * * Because we may not be keeping track of allocated/free inodes and * used filesystem blocks in the superblock, we do not mark the * superblock dirty in this transaction if we modify these fields. * We still need to update the transaction deltas so that they get * applied to the incore superblock, but we don't want them to * cause the superblock to get locked and logged if these are the * only fields in the superblock that the transaction modifies. */ void xfs_trans_mod_sb( xfs_trans_t *tp, uint field, int64_t delta) { uint32_t flags = (XFS_TRANS_DIRTY|XFS_TRANS_SB_DIRTY); xfs_mount_t *mp = tp->t_mountp; switch (field) { case XFS_TRANS_SB_ICOUNT: tp->t_icount_delta += delta; if (xfs_has_lazysbcount(mp)) flags &= ~XFS_TRANS_SB_DIRTY; break; case XFS_TRANS_SB_IFREE: tp->t_ifree_delta += delta; if (xfs_has_lazysbcount(mp)) flags &= ~XFS_TRANS_SB_DIRTY; break; case XFS_TRANS_SB_FDBLOCKS: /* * Track the number of blocks allocated in the transaction. * Make sure it does not exceed the number reserved. If so, * shutdown as this can lead to accounting inconsistency. */ if (delta < 0) { tp->t_blk_res_used += (uint)-delta; if (tp->t_blk_res_used > tp->t_blk_res) xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); } else if (delta > 0 && (tp->t_flags & XFS_TRANS_RES_FDBLKS)) { int64_t blkres_delta; /* * Return freed blocks directly to the reservation * instead of the global pool, being careful not to * overflow the trans counter. This is used to preserve * reservation across chains of transaction rolls that * repeatedly free and allocate blocks. */ blkres_delta = min_t(int64_t, delta, UINT_MAX - tp->t_blk_res); tp->t_blk_res += blkres_delta; delta -= blkres_delta; } tp->t_fdblocks_delta += delta; if (xfs_has_lazysbcount(mp)) flags &= ~XFS_TRANS_SB_DIRTY; break; case XFS_TRANS_SB_RES_FDBLOCKS: /* * The allocation has already been applied to the * in-core superblock's counter. This should only * be applied to the on-disk superblock. */ tp->t_res_fdblocks_delta += delta; if (xfs_has_lazysbcount(mp)) flags &= ~XFS_TRANS_SB_DIRTY; break; case XFS_TRANS_SB_FREXTENTS: /* * Track the number of blocks allocated in the * transaction. Make sure it does not exceed the * number reserved. */ if (delta < 0) { tp->t_rtx_res_used += (uint)-delta; ASSERT(tp->t_rtx_res_used <= tp->t_rtx_res); } tp->t_frextents_delta += delta; break; case XFS_TRANS_SB_RES_FREXTENTS: /* * The allocation has already been applied to the * in-core superblock's counter. This should only * be applied to the on-disk superblock. */ ASSERT(delta < 0); tp->t_res_frextents_delta += delta; break; case XFS_TRANS_SB_DBLOCKS: tp->t_dblocks_delta += delta; break; case XFS_TRANS_SB_AGCOUNT: ASSERT(delta > 0); tp->t_agcount_delta += delta; break; case XFS_TRANS_SB_IMAXPCT: tp->t_imaxpct_delta += delta; break; case XFS_TRANS_SB_REXTSIZE: tp->t_rextsize_delta += delta; break; case XFS_TRANS_SB_RBMBLOCKS: tp->t_rbmblocks_delta += delta; break; case XFS_TRANS_SB_RBLOCKS: tp->t_rblocks_delta += delta; break; case XFS_TRANS_SB_REXTENTS: tp->t_rextents_delta += delta; break; case XFS_TRANS_SB_REXTSLOG: tp->t_rextslog_delta += delta; break; default: ASSERT(0); return; } tp->t_flags |= flags; } /* * xfs_trans_apply_sb_deltas() is called from the commit code * to bring the superblock buffer into the current transaction * and modify it as requested by earlier calls to xfs_trans_mod_sb(). * * For now we just look at each field allowed to change and change * it if necessary. */ STATIC void xfs_trans_apply_sb_deltas( xfs_trans_t *tp) { struct xfs_dsb *sbp; struct xfs_buf *bp; int whole = 0; bp = xfs_trans_getsb(tp); sbp = bp->b_addr; /* * Only update the superblock counters if we are logging them */ if (!xfs_has_lazysbcount((tp->t_mountp))) { if (tp->t_icount_delta) be64_add_cpu(&sbp->sb_icount, tp->t_icount_delta); if (tp->t_ifree_delta) be64_add_cpu(&sbp->sb_ifree, tp->t_ifree_delta); if (tp->t_fdblocks_delta) be64_add_cpu(&sbp->sb_fdblocks, tp->t_fdblocks_delta); if (tp->t_res_fdblocks_delta) be64_add_cpu(&sbp->sb_fdblocks, tp->t_res_fdblocks_delta); } /* * Updating frextents requires careful handling because it does not * behave like the lazysb counters because we cannot rely on log * recovery in older kenels to recompute the value from the rtbitmap. * This means that the ondisk frextents must be consistent with the * rtbitmap. * * Therefore, log the frextents change to the ondisk superblock and * update the incore superblock so that future calls to xfs_log_sb * write the correct value ondisk. * * Don't touch m_frextents because it includes incore reservations, * and those are handled by the unreserve function. */ if (tp->t_frextents_delta || tp->t_res_frextents_delta) { struct xfs_mount *mp = tp->t_mountp; int64_t rtxdelta; rtxdelta = tp->t_frextents_delta + tp->t_res_frextents_delta; spin_lock(&mp->m_sb_lock); be64_add_cpu(&sbp->sb_frextents, rtxdelta); mp->m_sb.sb_frextents += rtxdelta; spin_unlock(&mp->m_sb_lock); } if (tp->t_dblocks_delta) { be64_add_cpu(&sbp->sb_dblocks, tp->t_dblocks_delta); whole = 1; } if (tp->t_agcount_delta) { be32_add_cpu(&sbp->sb_agcount, tp->t_agcount_delta); whole = 1; } if (tp->t_imaxpct_delta) { sbp->sb_imax_pct += tp->t_imaxpct_delta; whole = 1; } if (tp->t_rextsize_delta) { be32_add_cpu(&sbp->sb_rextsize, tp->t_rextsize_delta); whole = 1; } if (tp->t_rbmblocks_delta) { be32_add_cpu(&sbp->sb_rbmblocks, tp->t_rbmblocks_delta); whole = 1; } if (tp->t_rblocks_delta) { be64_add_cpu(&sbp->sb_rblocks, tp->t_rblocks_delta); whole = 1; } if (tp->t_rextents_delta) { be64_add_cpu(&sbp->sb_rextents, tp->t_rextents_delta); whole = 1; } if (tp->t_rextslog_delta) { sbp->sb_rextslog += tp->t_rextslog_delta; whole = 1; } xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); if (whole) /* * Log the whole thing, the fields are noncontiguous. */ xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb) - 1); else /* * Since all the modifiable fields are contiguous, we * can get away with this. */ xfs_trans_log_buf(tp, bp, offsetof(struct xfs_dsb, sb_icount), offsetof(struct xfs_dsb, sb_frextents) + sizeof(sbp->sb_frextents) - 1); } /* * xfs_trans_unreserve_and_mod_sb() is called to release unused reservations and * apply superblock counter changes to the in-core superblock. The * t_res_fdblocks_delta and t_res_frextents_delta fields are explicitly NOT * applied to the in-core superblock. The idea is that that has already been * done. * * If we are not logging superblock counters, then the inode allocated/free and * used block counts are not updated in the on disk superblock. In this case, * XFS_TRANS_SB_DIRTY will not be set when the transaction is updated but we * still need to update the incore superblock with the changes. * * Deltas for the inode count are +/-64, hence we use a large batch size of 128 * so we don't need to take the counter lock on every update. */ #define XFS_ICOUNT_BATCH 128 void xfs_trans_unreserve_and_mod_sb( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; int64_t blkdelta = tp->t_blk_res; int64_t rtxdelta = tp->t_rtx_res; int64_t idelta = 0; int64_t ifreedelta = 0; /* * Calculate the deltas. * * t_fdblocks_delta and t_frextents_delta can be positive or negative: * * - positive values indicate blocks freed in the transaction. * - negative values indicate blocks allocated in the transaction * * Negative values can only happen if the transaction has a block * reservation that covers the allocated block. The end result is * that the calculated delta values must always be positive and we * can only put back previous allocated or reserved blocks here. */ ASSERT(tp->t_blk_res || tp->t_fdblocks_delta >= 0); if (xfs_has_lazysbcount(mp) || (tp->t_flags & XFS_TRANS_SB_DIRTY)) { blkdelta += tp->t_fdblocks_delta; ASSERT(blkdelta >= 0); } ASSERT(tp->t_rtx_res || tp->t_frextents_delta >= 0); if (tp->t_flags & XFS_TRANS_SB_DIRTY) { rtxdelta += tp->t_frextents_delta; ASSERT(rtxdelta >= 0); } if (xfs_has_lazysbcount(mp) || (tp->t_flags & XFS_TRANS_SB_DIRTY)) { idelta = tp->t_icount_delta; ifreedelta = tp->t_ifree_delta; } /* apply the per-cpu counters */ if (blkdelta) xfs_add_fdblocks(mp, blkdelta); if (idelta) percpu_counter_add_batch(&mp->m_icount, idelta, XFS_ICOUNT_BATCH); if (ifreedelta) percpu_counter_add(&mp->m_ifree, ifreedelta); if (rtxdelta) xfs_add_frextents(mp, rtxdelta); if (!(tp->t_flags & XFS_TRANS_SB_DIRTY)) return; /* apply remaining deltas */ spin_lock(&mp->m_sb_lock); mp->m_sb.sb_fdblocks += tp->t_fdblocks_delta + tp->t_res_fdblocks_delta; mp->m_sb.sb_icount += idelta; mp->m_sb.sb_ifree += ifreedelta; /* * Do not touch sb_frextents here because we are dealing with incore * reservation. sb_frextents is not part of the lazy sb counters so it * must be consistent with the ondisk rtbitmap and must never include * incore reservations. */ mp->m_sb.sb_dblocks += tp->t_dblocks_delta; mp->m_sb.sb_agcount += tp->t_agcount_delta; mp->m_sb.sb_imax_pct += tp->t_imaxpct_delta; mp->m_sb.sb_rextsize += tp->t_rextsize_delta; if (tp->t_rextsize_delta) { mp->m_rtxblklog = log2_if_power2(mp->m_sb.sb_rextsize); mp->m_rtxblkmask = mask64_if_power2(mp->m_sb.sb_rextsize); } mp->m_sb.sb_rbmblocks += tp->t_rbmblocks_delta; mp->m_sb.sb_rblocks += tp->t_rblocks_delta; mp->m_sb.sb_rextents += tp->t_rextents_delta; mp->m_sb.sb_rextslog += tp->t_rextslog_delta; spin_unlock(&mp->m_sb_lock); /* * Debug checks outside of the spinlock so they don't lock up the * machine if they fail. */ ASSERT(mp->m_sb.sb_imax_pct >= 0); ASSERT(mp->m_sb.sb_rextslog >= 0); } /* Add the given log item to the transaction's list of log items. */ void xfs_trans_add_item( struct xfs_trans *tp, struct xfs_log_item *lip) { ASSERT(lip->li_log == tp->t_mountp->m_log); ASSERT(lip->li_ailp == tp->t_mountp->m_ail); ASSERT(list_empty(&lip->li_trans)); ASSERT(!test_bit(XFS_LI_DIRTY, &lip->li_flags)); list_add_tail(&lip->li_trans, &tp->t_items); trace_xfs_trans_add_item(tp, _RET_IP_); } /* * Unlink the log item from the transaction. the log item is no longer * considered dirty in this transaction, as the linked transaction has * finished, either by abort or commit completion. */ void xfs_trans_del_item( struct xfs_log_item *lip) { clear_bit(XFS_LI_DIRTY, &lip->li_flags); list_del_init(&lip->li_trans); } /* Detach and unlock all of the items in a transaction */ static void xfs_trans_free_items( struct xfs_trans *tp, bool abort) { struct xfs_log_item *lip, *next; trace_xfs_trans_free_items(tp, _RET_IP_); list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) { xfs_trans_del_item(lip); if (abort) set_bit(XFS_LI_ABORTED, &lip->li_flags); if (lip->li_ops->iop_release) lip->li_ops->iop_release(lip); } } /* * Sort transaction items prior to running precommit operations. This will * attempt to order the items such that they will always be locked in the same * order. Items that have no sort function are moved to the end of the list * and so are locked last. * * This may need refinement as different types of objects add sort functions. * * Function is more complex than it needs to be because we are comparing 64 bit * values and the function only returns 32 bit values. */ static int xfs_trans_precommit_sort( void *unused_arg, const struct list_head *a, const struct list_head *b) { struct xfs_log_item *lia = container_of(a, struct xfs_log_item, li_trans); struct xfs_log_item *lib = container_of(b, struct xfs_log_item, li_trans); int64_t diff; /* * If both items are non-sortable, leave them alone. If only one is * sortable, move the non-sortable item towards the end of the list. */ if (!lia->li_ops->iop_sort && !lib->li_ops->iop_sort) return 0; if (!lia->li_ops->iop_sort) return 1; if (!lib->li_ops->iop_sort) return -1; diff = lia->li_ops->iop_sort(lia) - lib->li_ops->iop_sort(lib); if (diff < 0) return -1; if (diff > 0) return 1; return 0; } /* * Run transaction precommit functions. * * If there is an error in any of the callouts, then stop immediately and * trigger a shutdown to abort the transaction. There is no recovery possible * from errors at this point as the transaction is dirty.... */ static int xfs_trans_run_precommits( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; struct xfs_log_item *lip, *n; int error = 0; /* * Sort the item list to avoid ABBA deadlocks with other transactions * running precommit operations that lock multiple shared items such as * inode cluster buffers. */ list_sort(NULL, &tp->t_items, xfs_trans_precommit_sort); /* * Precommit operations can remove the log item from the transaction * if the log item exists purely to delay modifications until they * can be ordered against other operations. Hence we have to use * list_for_each_entry_safe() here. */ list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) { if (!test_bit(XFS_LI_DIRTY, &lip->li_flags)) continue; if (lip->li_ops->iop_precommit) { error = lip->li_ops->iop_precommit(tp, lip); if (error) break; } } if (error) xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; } /* * Commit the given transaction to the log. * * XFS disk error handling mechanism is not based on a typical * transaction abort mechanism. Logically after the filesystem * gets marked 'SHUTDOWN', we can't let any new transactions * be durable - ie. committed to disk - because some metadata might * be inconsistent. In such cases, this returns an error, and the * caller may assume that all locked objects joined to the transaction * have already been unlocked as if the commit had succeeded. * Do not reference the transaction structure after this call. */ static int __xfs_trans_commit( struct xfs_trans *tp, bool regrant) { struct xfs_mount *mp = tp->t_mountp; struct xlog *log = mp->m_log; xfs_csn_t commit_seq = 0; int error = 0; int sync = tp->t_flags & XFS_TRANS_SYNC; trace_xfs_trans_commit(tp, _RET_IP_); error = xfs_trans_run_precommits(tp); if (error) { if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) xfs_defer_cancel(tp); goto out_unreserve; } /* * Finish deferred items on final commit. Only permanent transactions * should ever have deferred ops. */ WARN_ON_ONCE(!list_empty(&tp->t_dfops) && !(tp->t_flags & XFS_TRANS_PERM_LOG_RES)); if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) { error = xfs_defer_finish_noroll(&tp); if (error) goto out_unreserve; /* Run precommits from final tx in defer chain. */ error = xfs_trans_run_precommits(tp); if (error) goto out_unreserve; } /* * If there is nothing to be logged by the transaction, * then unlock all of the items associated with the * transaction and free the transaction structure. * Also make sure to return any reserved blocks to * the free pool. */ if (!(tp->t_flags & XFS_TRANS_DIRTY)) goto out_unreserve; /* * We must check against log shutdown here because we cannot abort log * items and leave them dirty, inconsistent and unpinned in memory while * the log is active. This leaves them open to being written back to * disk, and that will lead to on-disk corruption. */ if (xlog_is_shutdown(log)) { error = -EIO; goto out_unreserve; } ASSERT(tp->t_ticket != NULL); /* * If we need to update the superblock, then do it now. */ if (tp->t_flags & XFS_TRANS_SB_DIRTY) xfs_trans_apply_sb_deltas(tp); xfs_trans_apply_dquot_deltas(tp); xlog_cil_commit(log, tp, &commit_seq, regrant); xfs_trans_free(tp); /* * If the transaction needs to be synchronous, then force the * log out now and wait for it. */ if (sync) { error = xfs_log_force_seq(mp, commit_seq, XFS_LOG_SYNC, NULL); XFS_STATS_INC(mp, xs_trans_sync); } else { XFS_STATS_INC(mp, xs_trans_async); } return error; out_unreserve: xfs_trans_unreserve_and_mod_sb(tp); /* * It is indeed possible for the transaction to be not dirty but * the dqinfo portion to be. All that means is that we have some * (non-persistent) quota reservations that need to be unreserved. */ xfs_trans_unreserve_and_mod_dquots(tp); if (tp->t_ticket) { if (regrant && !xlog_is_shutdown(log)) xfs_log_ticket_regrant(log, tp->t_ticket); else xfs_log_ticket_ungrant(log, tp->t_ticket); tp->t_ticket = NULL; } xfs_trans_free_items(tp, !!error); xfs_trans_free(tp); XFS_STATS_INC(mp, xs_trans_empty); return error; } int xfs_trans_commit( struct xfs_trans *tp) { return __xfs_trans_commit(tp, false); } /* * Unlock all of the transaction's items and free the transaction. If the * transaction is dirty, we must shut down the filesystem because there is no * way to restore them to their previous state. * * If the transaction has made a log reservation, make sure to release it as * well. * * This is a high level function (equivalent to xfs_trans_commit()) and so can * be called after the transaction has effectively been aborted due to the mount * being shut down. However, if the mount has not been shut down and the * transaction is dirty we will shut the mount down and, in doing so, that * guarantees that the log is shut down, too. Hence we don't need to be as * careful with shutdown state and dirty items here as we need to be in * xfs_trans_commit(). */ void xfs_trans_cancel( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; struct xlog *log = mp->m_log; bool dirty = (tp->t_flags & XFS_TRANS_DIRTY); trace_xfs_trans_cancel(tp, _RET_IP_); /* * It's never valid to cancel a transaction with deferred ops attached, * because the transaction is effectively dirty. Complain about this * loudly before freeing the in-memory defer items and shutting down the * filesystem. */ if (!list_empty(&tp->t_dfops)) { ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); dirty = true; xfs_defer_cancel(tp); } /* * See if the caller is relying on us to shut down the filesystem. We * only want an error report if there isn't already a shutdown in * progress, so we only need to check against the mount shutdown state * here. */ if (dirty && !xfs_is_shutdown(mp)) { XFS_ERROR_REPORT("xfs_trans_cancel", XFS_ERRLEVEL_LOW, mp); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); } #ifdef DEBUG /* Log items need to be consistent until the log is shut down. */ if (!dirty && !xlog_is_shutdown(log)) { struct xfs_log_item *lip; list_for_each_entry(lip, &tp->t_items, li_trans) ASSERT(!xlog_item_is_intent_done(lip)); } #endif xfs_trans_unreserve_and_mod_sb(tp); xfs_trans_unreserve_and_mod_dquots(tp); if (tp->t_ticket) { xfs_log_ticket_ungrant(log, tp->t_ticket); tp->t_ticket = NULL; } xfs_trans_free_items(tp, dirty); xfs_trans_free(tp); } /* * Roll from one trans in the sequence of PERMANENT transactions to * the next: permanent transactions are only flushed out when * committed with xfs_trans_commit(), but we still want as soon * as possible to let chunks of it go to the log. So we commit the * chunk we've been working on and get a new transaction to continue. */ int xfs_trans_roll( struct xfs_trans **tpp) { struct xfs_trans *trans = *tpp; struct xfs_trans_res tres; int error; trace_xfs_trans_roll(trans, _RET_IP_); /* * Copy the critical parameters from one trans to the next. */ tres.tr_logres = trans->t_log_res; tres.tr_logcount = trans->t_log_count; *tpp = xfs_trans_dup(trans); /* * Commit the current transaction. * If this commit failed, then it'd just unlock those items that * are not marked ihold. That also means that a filesystem shutdown * is in progress. The caller takes the responsibility to cancel * the duplicate transaction that gets returned. */ error = __xfs_trans_commit(trans, true); if (error) return error; /* * Reserve space in the log for the next transaction. * This also pushes items in the "AIL", the list of logged items, * out to disk if they are taking up space at the tail of the log * that we want to use. This requires that either nothing be locked * across this call, or that anything that is locked be logged in * the prior and the next transactions. */ tres.tr_logflags = XFS_TRANS_PERM_LOG_RES; return xfs_trans_reserve(*tpp, &tres, 0, 0); } /* * Allocate an transaction, lock and join the inode to it, and reserve quota. * * The caller must ensure that the on-disk dquots attached to this inode have * already been allocated and initialized. The caller is responsible for * releasing ILOCK_EXCL if a new transaction is returned. */ int xfs_trans_alloc_inode( struct xfs_inode *ip, struct xfs_trans_res *resv, unsigned int dblocks, unsigned int rblocks, bool force, struct xfs_trans **tpp) { struct xfs_trans *tp; struct xfs_mount *mp = ip->i_mount; bool retried = false; int error; retry: error = xfs_trans_alloc(mp, resv, dblocks, xfs_extlen_to_rtxlen(mp, rblocks), force ? XFS_TRANS_RESERVE : 0, &tp); if (error) return error; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); error = xfs_qm_dqattach_locked(ip, false); if (error) { /* Caller should have allocated the dquots! */ ASSERT(error != -ENOENT); goto out_cancel; } error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks, force); if ((error == -EDQUOT || error == -ENOSPC) && !retried) { xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_blockgc_free_quota(ip, 0); retried = true; goto retry; } if (error) goto out_cancel; *tpp = tp; return 0; out_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } /* * Try to reserve more blocks for a transaction. * * This is for callers that need to attach resources to a transaction, scan * those resources to determine the space reservation requirements, and then * modify the attached resources. In other words, online repair. This can * fail due to ENOSPC, so the caller must be able to cancel the transaction * without shutting down the fs. */ int xfs_trans_reserve_more( struct xfs_trans *tp, unsigned int blocks, unsigned int rtextents) { struct xfs_trans_res resv = { }; return xfs_trans_reserve(tp, &resv, blocks, rtextents); } /* * Try to reserve more blocks and file quota for a transaction. Same * conditions of usage as xfs_trans_reserve_more. */ int xfs_trans_reserve_more_inode( struct xfs_trans *tp, struct xfs_inode *ip, unsigned int dblocks, unsigned int rblocks, bool force_quota) { struct xfs_trans_res resv = { }; struct xfs_mount *mp = ip->i_mount; unsigned int rtx = xfs_extlen_to_rtxlen(mp, rblocks); int error; xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); error = xfs_trans_reserve(tp, &resv, dblocks, rtx); if (error) return error; if (!XFS_IS_QUOTA_ON(mp) || xfs_is_quota_inode(&mp->m_sb, ip->i_ino)) return 0; if (tp->t_flags & XFS_TRANS_RESERVE) force_quota = true; error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks, force_quota); if (!error) return 0; /* Quota failed, give back the new reservation. */ xfs_add_fdblocks(mp, dblocks); tp->t_blk_res -= dblocks; xfs_add_frextents(mp, rtx); tp->t_rtx_res -= rtx; return error; } /* * Allocate an transaction in preparation for inode creation by reserving quota * against the given dquots. Callers are not required to hold any inode locks. */ int xfs_trans_alloc_icreate( struct xfs_mount *mp, struct xfs_trans_res *resv, struct xfs_dquot *udqp, struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, unsigned int dblocks, struct xfs_trans **tpp) { struct xfs_trans *tp; bool retried = false; int error; retry: error = xfs_trans_alloc(mp, resv, dblocks, 0, 0, &tp); if (error) return error; error = xfs_trans_reserve_quota_icreate(tp, udqp, gdqp, pdqp, dblocks); if ((error == -EDQUOT || error == -ENOSPC) && !retried) { xfs_trans_cancel(tp); xfs_blockgc_free_dquots(mp, udqp, gdqp, pdqp, 0); retried = true; goto retry; } if (error) { xfs_trans_cancel(tp); return error; } *tpp = tp; return 0; } /* * Allocate an transaction, lock and join the inode to it, and reserve quota * in preparation for inode attribute changes that include uid, gid, or prid * changes. * * The caller must ensure that the on-disk dquots attached to this inode have * already been allocated and initialized. The ILOCK will be dropped when the * transaction is committed or cancelled. */ int xfs_trans_alloc_ichange( struct xfs_inode *ip, struct xfs_dquot *new_udqp, struct xfs_dquot *new_gdqp, struct xfs_dquot *new_pdqp, bool force, struct xfs_trans **tpp) { struct xfs_trans *tp; struct xfs_mount *mp = ip->i_mount; struct xfs_dquot *udqp; struct xfs_dquot *gdqp; struct xfs_dquot *pdqp; bool retried = false; int error; retry: error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); if (error) return error; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); error = xfs_qm_dqattach_locked(ip, false); if (error) { /* Caller should have allocated the dquots! */ ASSERT(error != -ENOENT); goto out_cancel; } /* * For each quota type, skip quota reservations if the inode's dquots * now match the ones that came from the caller, or the caller didn't * pass one in. The inode's dquots can change if we drop the ILOCK to * perform a blockgc scan, so we must preserve the caller's arguments. */ udqp = (new_udqp != ip->i_udquot) ? new_udqp : NULL; gdqp = (new_gdqp != ip->i_gdquot) ? new_gdqp : NULL; pdqp = (new_pdqp != ip->i_pdquot) ? new_pdqp : NULL; if (udqp || gdqp || pdqp) { unsigned int qflags = XFS_QMOPT_RES_REGBLKS; if (force) qflags |= XFS_QMOPT_FORCE_RES; /* * Reserve enough quota to handle blocks on disk and reserved * for a delayed allocation. We'll actually transfer the * delalloc reservation between dquots at chown time, even * though that part is only semi-transactional. */ error = xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp, pdqp, ip->i_nblocks + ip->i_delayed_blks, 1, qflags); if ((error == -EDQUOT || error == -ENOSPC) && !retried) { xfs_trans_cancel(tp); xfs_blockgc_free_dquots(mp, udqp, gdqp, pdqp, 0); retried = true; goto retry; } if (error) goto out_cancel; } *tpp = tp; return 0; out_cancel: xfs_trans_cancel(tp); return error; } /* * Allocate an transaction, lock and join the directory and child inodes to it, * and reserve quota for a directory update. If there isn't sufficient space, * @dblocks will be set to zero for a reservationless directory update and * @nospace_error will be set to a negative errno describing the space * constraint we hit. * * The caller must ensure that the on-disk dquots attached to this inode have * already been allocated and initialized. The ILOCKs will be dropped when the * transaction is committed or cancelled. * * Caller is responsible for unlocking the inodes manually upon return */ int xfs_trans_alloc_dir( struct xfs_inode *dp, struct xfs_trans_res *resv, struct xfs_inode *ip, unsigned int *dblocks, struct xfs_trans **tpp, int *nospace_error) { struct xfs_trans *tp; struct xfs_mount *mp = ip->i_mount; unsigned int resblks; bool retried = false; int error; retry: *nospace_error = 0; resblks = *dblocks; error = xfs_trans_alloc(mp, resv, resblks, 0, 0, &tp); if (error == -ENOSPC) { *nospace_error = error; resblks = 0; error = xfs_trans_alloc(mp, resv, resblks, 0, 0, &tp); } if (error) return error; xfs_lock_two_inodes(dp, XFS_ILOCK_EXCL, ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, dp, 0); xfs_trans_ijoin(tp, ip, 0); error = xfs_qm_dqattach_locked(dp, false); if (error) { /* Caller should have allocated the dquots! */ ASSERT(error != -ENOENT); goto out_cancel; } error = xfs_qm_dqattach_locked(ip, false); if (error) { /* Caller should have allocated the dquots! */ ASSERT(error != -ENOENT); goto out_cancel; } if (resblks == 0) goto done; error = xfs_trans_reserve_quota_nblks(tp, dp, resblks, 0, false); if (error == -EDQUOT || error == -ENOSPC) { if (!retried) { xfs_trans_cancel(tp); xfs_iunlock(dp, XFS_ILOCK_EXCL); if (dp != ip) xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_blockgc_free_quota(dp, 0); retried = true; goto retry; } *nospace_error = error; resblks = 0; error = 0; } if (error) goto out_cancel; done: *tpp = tp; *dblocks = resblks; return 0; out_cancel: xfs_trans_cancel(tp); return error; } |
| 1 1 1 1 1 1 1 4 4 4 4 4 1 1 1 1 7 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ #ifndef __HCI_CORE_H #define __HCI_CORE_H #include <linux/idr.h> #include <linux/leds.h> #include <linux/rculist.h> #include <net/bluetooth/hci.h> #include <net/bluetooth/hci_sync.h> #include <net/bluetooth/hci_sock.h> #include <net/bluetooth/coredump.h> /* HCI priority */ #define HCI_PRIO_MAX 7 /* HCI maximum id value */ #define HCI_MAX_ID 10000 /* HCI Core structures */ struct inquiry_data { bdaddr_t bdaddr; __u8 pscan_rep_mode; __u8 pscan_period_mode; __u8 pscan_mode; __u8 dev_class[3]; __le16 clock_offset; __s8 rssi; __u8 ssp_mode; }; struct inquiry_entry { struct list_head all; /* inq_cache.all */ struct list_head list; /* unknown or resolve */ enum { NAME_NOT_KNOWN, NAME_NEEDED, NAME_PENDING, NAME_KNOWN, } name_state; __u32 timestamp; struct inquiry_data data; }; struct discovery_state { int type; enum { DISCOVERY_STOPPED, DISCOVERY_STARTING, DISCOVERY_FINDING, DISCOVERY_RESOLVING, DISCOVERY_STOPPING, } state; struct list_head all; /* All devices found during inquiry */ struct list_head unknown; /* Name state not known */ struct list_head resolve; /* Name needs to be resolved */ __u32 timestamp; bdaddr_t last_adv_addr; u8 last_adv_addr_type; s8 last_adv_rssi; u32 last_adv_flags; u8 last_adv_data[HCI_MAX_EXT_AD_LENGTH]; u8 last_adv_data_len; bool report_invalid_rssi; bool result_filtering; bool limited; s8 rssi; u16 uuid_count; u8 (*uuids)[16]; unsigned long name_resolve_timeout; }; #define SUSPEND_NOTIFIER_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ enum suspend_tasks { SUSPEND_PAUSE_DISCOVERY, SUSPEND_UNPAUSE_DISCOVERY, SUSPEND_PAUSE_ADVERTISING, SUSPEND_UNPAUSE_ADVERTISING, SUSPEND_SCAN_DISABLE, SUSPEND_SCAN_ENABLE, SUSPEND_DISCONNECTING, SUSPEND_POWERING_DOWN, SUSPEND_PREPARE_NOTIFIER, SUSPEND_SET_ADV_FILTER, __SUSPEND_NUM_TASKS }; enum suspended_state { BT_RUNNING = 0, BT_SUSPEND_DISCONNECT, BT_SUSPEND_CONFIGURE_WAKE, }; struct hci_conn_hash { struct list_head list; unsigned int acl_num; unsigned int sco_num; unsigned int iso_num; unsigned int le_num; unsigned int le_num_peripheral; }; struct bdaddr_list { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; }; struct codec_list { struct list_head list; u8 id; __u16 cid; __u16 vid; u8 transport; u8 num_caps; u32 len; struct hci_codec_caps caps[]; }; struct bdaddr_list_with_irk { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; u8 peer_irk[16]; u8 local_irk[16]; }; /* Bitmask of connection flags */ enum hci_conn_flags { HCI_CONN_FLAG_REMOTE_WAKEUP = 1, HCI_CONN_FLAG_DEVICE_PRIVACY = 2, }; typedef u8 hci_conn_flags_t; struct bdaddr_list_with_flags { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; hci_conn_flags_t flags; }; struct bt_uuid { struct list_head list; u8 uuid[16]; u8 size; u8 svc_hint; }; struct blocked_key { struct list_head list; struct rcu_head rcu; u8 type; u8 val[16]; }; struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; u8 link_type; u8 type; u8 val[16]; }; struct smp_ltk { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; u8 link_type; u8 authenticated; u8 type; u8 enc_size; __le16 ediv; __le64 rand; u8 val[16]; }; struct smp_irk { struct list_head list; struct rcu_head rcu; bdaddr_t rpa; bdaddr_t bdaddr; u8 addr_type; u8 link_type; u8 val[16]; }; struct link_key { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; u8 link_type; u8 type; u8 val[HCI_LINK_KEY_SIZE]; u8 pin_len; }; struct oob_data { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; u8 present; u8 hash192[16]; u8 rand192[16]; u8 hash256[16]; u8 rand256[16]; }; struct adv_info { struct list_head list; bool enabled; bool pending; bool periodic; __u8 mesh; __u8 instance; __u8 handle; __u32 flags; __u16 timeout; __u16 remaining_time; __u16 duration; __u16 adv_data_len; __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; bool adv_data_changed; __u16 scan_rsp_len; __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH]; bool scan_rsp_changed; __u16 per_adv_data_len; __u8 per_adv_data[HCI_MAX_PER_AD_LENGTH]; __s8 tx_power; __u32 min_interval; __u32 max_interval; bdaddr_t random_addr; bool rpa_expired; struct delayed_work rpa_expired_cb; }; #define HCI_MAX_ADV_INSTANCES 5 #define HCI_DEFAULT_ADV_DURATION 2 #define HCI_ADV_TX_POWER_NO_PREFERENCE 0x7F #define DATA_CMP(_d1, _l1, _d2, _l2) \ (_l1 == _l2 ? memcmp(_d1, _d2, _l1) : _l1 - _l2) #define ADV_DATA_CMP(_adv, _data, _len) \ DATA_CMP((_adv)->adv_data, (_adv)->adv_data_len, _data, _len) #define SCAN_RSP_CMP(_adv, _data, _len) \ DATA_CMP((_adv)->scan_rsp_data, (_adv)->scan_rsp_len, _data, _len) struct monitored_device { struct list_head list; bdaddr_t bdaddr; __u8 addr_type; __u16 handle; bool notified; }; struct adv_pattern { struct list_head list; __u8 ad_type; __u8 offset; __u8 length; __u8 value[HCI_MAX_EXT_AD_LENGTH]; }; struct adv_rssi_thresholds { __s8 low_threshold; __s8 high_threshold; __u16 low_threshold_timeout; __u16 high_threshold_timeout; __u8 sampling_period; }; struct adv_monitor { struct list_head patterns; struct adv_rssi_thresholds rssi; __u16 handle; enum { ADV_MONITOR_STATE_NOT_REGISTERED, ADV_MONITOR_STATE_REGISTERED, ADV_MONITOR_STATE_OFFLOADED } state; }; #define HCI_MIN_ADV_MONITOR_HANDLE 1 #define HCI_MAX_ADV_MONITOR_NUM_HANDLES 32 #define HCI_MAX_ADV_MONITOR_NUM_PATTERNS 16 #define HCI_ADV_MONITOR_EXT_NONE 1 #define HCI_ADV_MONITOR_EXT_MSFT 2 #define HCI_MAX_SHORT_NAME_LENGTH 10 #define HCI_CONN_HANDLE_MAX 0x0eff #define HCI_CONN_HANDLE_UNSET(_handle) (_handle > HCI_CONN_HANDLE_MAX) /* Min encryption key size to match with SMP */ #define HCI_MIN_ENC_KEY_SIZE 7 /* Default LE RPA expiry time, 15 minutes */ #define HCI_DEFAULT_RPA_TIMEOUT (15 * 60) /* Default min/max age of connection information (1s/3s) */ #define DEFAULT_CONN_INFO_MIN_AGE 1000 #define DEFAULT_CONN_INFO_MAX_AGE 3000 /* Default authenticated payload timeout 30s */ #define DEFAULT_AUTH_PAYLOAD_TIMEOUT 0x0bb8 #define HCI_MAX_PAGES 3 struct hci_dev { struct list_head list; struct mutex lock; struct ida unset_handle_ida; const char *name; unsigned long flags; __u16 id; __u8 bus; bdaddr_t bdaddr; bdaddr_t setup_addr; bdaddr_t public_addr; bdaddr_t random_addr; bdaddr_t static_addr; __u8 adv_addr_type; __u8 dev_name[HCI_MAX_NAME_LENGTH]; __u8 short_name[HCI_MAX_SHORT_NAME_LENGTH]; __u8 eir[HCI_MAX_EIR_LENGTH]; __u16 appearance; __u8 dev_class[3]; __u8 major_class; __u8 minor_class; __u8 max_page; __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[8]; __u8 le_accept_list_size; __u8 le_resolv_list_size; __u8 le_num_of_adv_sets; __u8 le_states[8]; __u8 mesh_ad_types[16]; __u8 mesh_send_ref; __u8 commands[64]; __u8 hci_ver; __u16 hci_rev; __u8 lmp_ver; __u16 manufacturer; __u16 lmp_subver; __u16 voice_setting; __u8 num_iac; __u16 stored_max_keys; __u16 stored_num_keys; __u8 io_capability; __s8 inq_tx_power; __u8 err_data_reporting; __u16 page_scan_interval; __u16 page_scan_window; __u8 page_scan_type; __u8 le_adv_channel_map; __u16 le_adv_min_interval; __u16 le_adv_max_interval; __u8 le_scan_type; __u16 le_scan_interval; __u16 le_scan_window; __u16 le_scan_int_suspend; __u16 le_scan_window_suspend; __u16 le_scan_int_discovery; __u16 le_scan_window_discovery; __u16 le_scan_int_adv_monitor; __u16 le_scan_window_adv_monitor; __u16 le_scan_int_connect; __u16 le_scan_window_connect; __u16 le_conn_min_interval; __u16 le_conn_max_interval; __u16 le_conn_latency; __u16 le_supv_timeout; __u16 le_def_tx_len; __u16 le_def_tx_time; __u16 le_max_tx_len; __u16 le_max_tx_time; __u16 le_max_rx_len; __u16 le_max_rx_time; __u8 le_max_key_size; __u8 le_min_key_size; __u16 discov_interleaved_timeout; __u16 conn_info_min_age; __u16 conn_info_max_age; __u16 auth_payload_timeout; __u8 min_enc_key_size; __u8 max_enc_key_size; __u8 pairing_opts; __u8 ssp_debug_mode; __u8 hw_error_code; __u32 clock; __u16 advmon_allowlist_duration; __u16 advmon_no_filter_duration; __u8 enable_advmon_interleave_scan; __u16 devid_source; __u16 devid_vendor; __u16 devid_product; __u16 devid_version; __u8 def_page_scan_type; __u16 def_page_scan_int; __u16 def_page_scan_window; __u8 def_inq_scan_type; __u16 def_inq_scan_int; __u16 def_inq_scan_window; __u16 def_br_lsto; __u16 def_page_timeout; __u16 def_multi_adv_rotation_duration; __u16 def_le_autoconnect_timeout; __s8 min_le_tx_power; __s8 max_le_tx_power; __u16 pkt_type; __u16 esco_type; __u16 link_policy; __u16 link_mode; __u32 idle_timeout; __u16 sniff_min_interval; __u16 sniff_max_interval; unsigned int auto_accept_delay; unsigned long quirks; atomic_t cmd_cnt; unsigned int acl_cnt; unsigned int sco_cnt; unsigned int le_cnt; unsigned int iso_cnt; unsigned int acl_mtu; unsigned int sco_mtu; unsigned int le_mtu; unsigned int iso_mtu; unsigned int acl_pkts; unsigned int sco_pkts; unsigned int le_pkts; unsigned int iso_pkts; unsigned long acl_last_tx; unsigned long le_last_tx; __u8 le_tx_def_phys; __u8 le_rx_def_phys; struct workqueue_struct *workqueue; struct workqueue_struct *req_workqueue; struct work_struct power_on; struct delayed_work power_off; struct work_struct error_reset; struct work_struct cmd_sync_work; struct list_head cmd_sync_work_list; struct mutex cmd_sync_work_lock; struct mutex unregister_lock; struct work_struct cmd_sync_cancel_work; struct work_struct reenable_adv_work; __u16 discov_timeout; struct delayed_work discov_off; struct delayed_work service_cache; struct delayed_work cmd_timer; struct delayed_work ncmd_timer; struct work_struct rx_work; struct work_struct cmd_work; struct work_struct tx_work; struct delayed_work le_scan_disable; struct sk_buff_head rx_q; struct sk_buff_head raw_q; struct sk_buff_head cmd_q; struct sk_buff *sent_cmd; struct sk_buff *recv_event; struct mutex req_lock; wait_queue_head_t req_wait_q; __u32 req_status; __u32 req_result; struct sk_buff *req_skb; struct sk_buff *req_rsp; void *smp_data; void *smp_bredr_data; struct discovery_state discovery; bool discovery_paused; int advertising_old_state; bool advertising_paused; struct notifier_block suspend_notifier; enum suspended_state suspend_state_next; enum suspended_state suspend_state; bool scanning_paused; bool suspended; u8 wake_reason; bdaddr_t wake_addr; u8 wake_addr_type; struct hci_conn_hash conn_hash; struct list_head mesh_pending; struct list_head mgmt_pending; struct list_head reject_list; struct list_head accept_list; struct list_head uuids; struct list_head link_keys; struct list_head long_term_keys; struct list_head identity_resolving_keys; struct list_head remote_oob_data; struct list_head le_accept_list; struct list_head le_resolv_list; struct list_head le_conn_params; struct list_head pend_le_conns; struct list_head pend_le_reports; struct list_head blocked_keys; struct list_head local_codecs; struct hci_dev_stats stat; atomic_t promisc; const char *hw_info; const char *fw_info; struct dentry *debugfs; struct hci_devcoredump dump; struct device dev; struct rfkill *rfkill; DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); hci_conn_flags_t conn_flags; __s8 adv_tx_power; __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 adv_data_len; __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH]; __u8 scan_rsp_data_len; __u8 per_adv_data[HCI_MAX_PER_AD_LENGTH]; __u8 per_adv_data_len; struct list_head adv_instances; unsigned int adv_instance_cnt; __u8 cur_adv_instance; __u16 adv_instance_timeout; struct delayed_work adv_instance_expire; struct idr adv_monitors_idr; unsigned int adv_monitors_cnt; __u8 irk[16]; __u32 rpa_timeout; struct delayed_work rpa_expired; bdaddr_t rpa; struct delayed_work mesh_send_done; enum { INTERLEAVE_SCAN_NONE, INTERLEAVE_SCAN_NO_FILTER, INTERLEAVE_SCAN_ALLOWLIST } interleave_scan_state; struct delayed_work interleave_scan; struct list_head monitored_devices; bool advmon_pend_notify; #if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; #endif #if IS_ENABLED(CONFIG_BT_MSFTEXT) __u16 msft_opcode; void *msft_data; bool msft_curve_validity; #endif #if IS_ENABLED(CONFIG_BT_AOSPEXT) bool aosp_capable; bool aosp_quality_report; #endif int (*open)(struct hci_dev *hdev); int (*close)(struct hci_dev *hdev); int (*flush)(struct hci_dev *hdev); int (*setup)(struct hci_dev *hdev); int (*shutdown)(struct hci_dev *hdev); int (*send)(struct hci_dev *hdev, struct sk_buff *skb); void (*notify)(struct hci_dev *hdev, unsigned int evt); void (*hw_error)(struct hci_dev *hdev, u8 code); int (*post_init)(struct hci_dev *hdev); int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); void (*cmd_timeout)(struct hci_dev *hdev); void (*reset)(struct hci_dev *hdev); bool (*wakeup)(struct hci_dev *hdev); int (*set_quality_report)(struct hci_dev *hdev, bool enable); int (*get_data_path_id)(struct hci_dev *hdev, __u8 *data_path); int (*get_codec_config_data)(struct hci_dev *hdev, __u8 type, struct bt_codec *codec, __u8 *vnd_len, __u8 **vnd_data); u8 (*classify_pkt_type)(struct hci_dev *hdev, struct sk_buff *skb); }; #define HCI_PHY_HANDLE(handle) (handle & 0xff) enum conn_reasons { CONN_REASON_PAIR_DEVICE, CONN_REASON_L2CAP_CHAN, CONN_REASON_SCO_CONNECT, CONN_REASON_ISO_CONNECT, }; struct hci_conn { struct list_head list; atomic_t refcnt; bdaddr_t dst; __u8 dst_type; bdaddr_t src; __u8 src_type; bdaddr_t init_addr; __u8 init_addr_type; bdaddr_t resp_addr; __u8 resp_addr_type; __u8 adv_instance; __u16 handle; __u16 sync_handle; __u16 state; __u16 mtu; __u8 mode; __u8 type; __u8 role; bool out; __u8 attempt; __u8 dev_class[3]; __u8 features[HCI_MAX_PAGES][8]; __u16 pkt_type; __u16 link_policy; __u8 key_type; __u8 auth_type; __u8 sec_level; __u8 pending_sec_level; __u8 pin_length; __u8 enc_key_size; __u8 io_capability; __u32 passkey_notify; __u8 passkey_entered; __u16 disc_timeout; __u16 conn_timeout; __u16 setting; __u16 auth_payload_timeout; __u16 le_conn_min_interval; __u16 le_conn_max_interval; __u16 le_conn_interval; __u16 le_conn_latency; __u16 le_supv_timeout; __u8 le_adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 le_adv_data_len; __u8 le_per_adv_data[HCI_MAX_PER_AD_TOT_LEN]; __u16 le_per_adv_data_len; __u16 le_per_adv_data_offset; __u8 le_adv_phy; __u8 le_adv_sec_phy; __u8 le_tx_phy; __u8 le_rx_phy; __s8 rssi; __s8 tx_power; __s8 max_tx_power; struct bt_iso_qos iso_qos; unsigned long flags; enum conn_reasons conn_reason; __u8 abort_reason; __u32 clock; __u16 clock_accuracy; unsigned long conn_info_timestamp; __u8 remote_cap; __u8 remote_auth; __u8 remote_id; unsigned int sent; struct sk_buff_head data_q; struct list_head chan_list; struct delayed_work disc_work; struct delayed_work auto_accept_work; struct delayed_work idle_work; struct delayed_work le_conn_timeout; struct device dev; struct dentry *debugfs; struct hci_dev *hdev; void *l2cap_data; void *sco_data; void *iso_data; struct list_head link_list; struct hci_conn *parent; struct hci_link *link; struct bt_codec codec; void (*connect_cfm_cb) (struct hci_conn *conn, u8 status); void (*security_cfm_cb) (struct hci_conn *conn, u8 status); void (*disconn_cfm_cb) (struct hci_conn *conn, u8 reason); void (*cleanup)(struct hci_conn *conn); }; struct hci_link { struct list_head list; struct hci_conn *conn; }; struct hci_chan { struct list_head list; __u16 handle; struct hci_conn *conn; struct sk_buff_head data_q; unsigned int sent; __u8 state; }; struct hci_conn_params { struct list_head list; struct list_head action; bdaddr_t addr; u8 addr_type; u16 conn_min_interval; u16 conn_max_interval; u16 conn_latency; u16 supervision_timeout; enum { HCI_AUTO_CONN_DISABLED, HCI_AUTO_CONN_REPORT, HCI_AUTO_CONN_DIRECT, HCI_AUTO_CONN_ALWAYS, HCI_AUTO_CONN_LINK_LOSS, HCI_AUTO_CONN_EXPLICIT, } auto_connect; struct hci_conn *conn; bool explicit_connect; /* Accessed without hdev->lock: */ hci_conn_flags_t flags; u8 privacy_mode; }; extern struct list_head hci_dev_list; extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; extern struct mutex hci_cb_list_lock; #define hci_dev_set_flag(hdev, nr) set_bit((nr), (hdev)->dev_flags) #define hci_dev_clear_flag(hdev, nr) clear_bit((nr), (hdev)->dev_flags) #define hci_dev_change_flag(hdev, nr) change_bit((nr), (hdev)->dev_flags) #define hci_dev_test_flag(hdev, nr) test_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_set_flag(hdev, nr) test_and_set_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_clear_flag(hdev, nr) test_and_clear_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), (hdev)->dev_flags) #define hci_dev_clear_volatile_flags(hdev) \ do { \ hci_dev_clear_flag(hdev, HCI_LE_SCAN); \ hci_dev_clear_flag(hdev, HCI_LE_ADV); \ hci_dev_clear_flag(hdev, HCI_LL_RPA_RESOLUTION);\ hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); \ hci_dev_clear_flag(hdev, HCI_QUALITY_REPORT); \ } while (0) #define hci_dev_le_state_simultaneous(hdev) \ (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \ (hdev->le_states[4] & 0x08) && /* Central */ \ (hdev->le_states[4] & 0x40) && /* Peripheral */ \ (hdev->le_states[3] & 0x10)) /* Simultaneous */ /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); int l2cap_disconn_ind(struct hci_conn *hcon); void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); #if IS_ENABLED(CONFIG_BT_BREDR) int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb); #else static inline int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { return 0; } static inline void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) { } #endif #if IS_ENABLED(CONFIG_BT_LE) int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); #else static inline int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { return 0; } static inline void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) { } #endif /* ----- Inquiry cache ----- */ #define INQUIRY_CACHE_AGE_MAX (HZ*30) /* 30 seconds */ #define INQUIRY_ENTRY_AGE_MAX (HZ*60) /* 60 seconds */ static inline void discovery_init(struct hci_dev *hdev) { hdev->discovery.state = DISCOVERY_STOPPED; INIT_LIST_HEAD(&hdev->discovery.all); INIT_LIST_HEAD(&hdev->discovery.unknown); INIT_LIST_HEAD(&hdev->discovery.resolve); hdev->discovery.report_invalid_rssi = true; hdev->discovery.rssi = HCI_RSSI_INVALID; } static inline void hci_discovery_filter_clear(struct hci_dev *hdev) { hdev->discovery.result_filtering = false; hdev->discovery.report_invalid_rssi = true; hdev->discovery.rssi = HCI_RSSI_INVALID; hdev->discovery.uuid_count = 0; kfree(hdev->discovery.uuids); hdev->discovery.uuids = NULL; } bool hci_discovery_active(struct hci_dev *hdev); void hci_discovery_set_state(struct hci_dev *hdev, int state); static inline int inquiry_cache_empty(struct hci_dev *hdev) { return list_empty(&hdev->discovery.all); } static inline long inquiry_cache_age(struct hci_dev *hdev) { struct discovery_state *c = &hdev->discovery; return jiffies - c->timestamp; } static inline long inquiry_entry_age(struct inquiry_entry *e) { return jiffies - e->timestamp; } struct inquiry_entry *hci_inquiry_cache_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr); struct inquiry_entry *hci_inquiry_cache_lookup_unknown(struct hci_dev *hdev, bdaddr_t *bdaddr); struct inquiry_entry *hci_inquiry_cache_lookup_resolve(struct hci_dev *hdev, bdaddr_t *bdaddr, int state); void hci_inquiry_cache_update_resolve(struct hci_dev *hdev, struct inquiry_entry *ie); u32 hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, bool name_known); void hci_inquiry_cache_flush(struct hci_dev *hdev); /* ----- HCI Connections ----- */ enum { HCI_CONN_AUTH_PEND, HCI_CONN_ENCRYPT_PEND, HCI_CONN_RSWITCH_PEND, HCI_CONN_MODE_CHANGE_PEND, HCI_CONN_SCO_SETUP_PEND, HCI_CONN_MGMT_CONNECTED, HCI_CONN_SSP_ENABLED, HCI_CONN_SC_ENABLED, HCI_CONN_AES_CCM, HCI_CONN_POWER_SAVE, HCI_CONN_FLUSH_KEY, HCI_CONN_ENCRYPT, HCI_CONN_AUTH, HCI_CONN_SECURE, HCI_CONN_FIPS, HCI_CONN_STK_ENCRYPT, HCI_CONN_AUTH_INITIATOR, HCI_CONN_DROP, HCI_CONN_CANCEL, HCI_CONN_PARAM_REMOVAL_PEND, HCI_CONN_NEW_LINK_KEY, HCI_CONN_SCANNING, HCI_CONN_AUTH_FAILURE, HCI_CONN_PER_ADV, HCI_CONN_BIG_CREATED, HCI_CONN_CREATE_CIS, HCI_CONN_BIG_SYNC, HCI_CONN_BIG_SYNC_FAILED, HCI_CONN_PA_SYNC, HCI_CONN_PA_SYNC_FAILED, }; static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; return hci_dev_test_flag(hdev, HCI_SSP_ENABLED) && test_bit(HCI_CONN_SSP_ENABLED, &conn->flags); } static inline bool hci_conn_sc_enabled(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; return hci_dev_test_flag(hdev, HCI_SC_ENABLED) && test_bit(HCI_CONN_SC_ENABLED, &conn->flags); } static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) { struct hci_conn_hash *h = &hdev->conn_hash; list_add_tail_rcu(&c->list, &h->list); switch (c->type) { case ACL_LINK: h->acl_num++; break; case LE_LINK: h->le_num++; if (c->role == HCI_ROLE_SLAVE) h->le_num_peripheral++; break; case SCO_LINK: case ESCO_LINK: h->sco_num++; break; case ISO_LINK: h->iso_num++; break; } } static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) { struct hci_conn_hash *h = &hdev->conn_hash; list_del_rcu(&c->list); synchronize_rcu(); switch (c->type) { case ACL_LINK: h->acl_num--; break; case LE_LINK: h->le_num--; if (c->role == HCI_ROLE_SLAVE) h->le_num_peripheral--; break; case SCO_LINK: case ESCO_LINK: h->sco_num--; break; case ISO_LINK: h->iso_num--; break; } } static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type) { struct hci_conn_hash *h = &hdev->conn_hash; switch (type) { case ACL_LINK: return h->acl_num; case LE_LINK: return h->le_num; case SCO_LINK: case ESCO_LINK: return h->sco_num; case ISO_LINK: return h->iso_num; default: return 0; } } static inline unsigned int hci_conn_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; return c->acl_num + c->sco_num + c->le_num + c->iso_num; } static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c == conn) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } static inline __u8 hci_conn_lookup_type(struct hci_dev *hdev, __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; __u8 type = INVALID_LINK; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->handle == handle) { type = c->type; break; } } rcu_read_unlock(); return type; } static inline struct hci_conn *hci_conn_hash_lookup_bis(struct hci_dev *hdev, bdaddr_t *ba, __u8 bis) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (bacmp(&c->dst, ba) || c->type != ISO_LINK) continue; if (c->iso_qos.bcast.bis == bis) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_per_adv_bis(struct hci_dev *hdev, bdaddr_t *ba, __u8 big, __u8 bis) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (bacmp(&c->dst, ba) || c->type != ISO_LINK || !test_bit(HCI_CONN_PER_ADV, &c->flags)) continue; if (c->iso_qos.bcast.big == big && c->iso_qos.bcast.bis == bis) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_handle(struct hci_dev *hdev, __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->handle == handle) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_ba(struct hci_dev *hdev, __u8 type, bdaddr_t *ba) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && !bacmp(&c->dst, ba)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_le(struct hci_dev *hdev, bdaddr_t *ba, __u8 ba_type) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != LE_LINK) continue; if (ba_type == c->dst_type && !bacmp(&c->dst, ba)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, bdaddr_t *ba, __u8 ba_type, __u8 cig, __u8 id) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY)) continue; /* Match CIG ID if set */ if (cig != c->iso_qos.ucast.cig) continue; /* Match CIS ID if set */ if (id != c->iso_qos.ucast.cis) continue; /* Match destination address if set */ if (!ba || (ba_type == c->dst_type && !bacmp(&c->dst, ba))) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_cig(struct hci_dev *hdev, __u8 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != ISO_LINK || !bacmp(&c->dst, BDADDR_ANY)) continue; if (handle == c->iso_qos.ucast.cig) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, __u8 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (bacmp(&c->dst, BDADDR_ANY) || c->type != ISO_LINK) continue; if (handle == c->iso_qos.bcast.big) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle, __u16 state) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (bacmp(&c->dst, BDADDR_ANY) || c->type != ISO_LINK || c->state != state) continue; if (handle == c->iso_qos.bcast.big) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_pa_sync_big_handle(struct hci_dev *hdev, __u8 big) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != ISO_LINK || !test_bit(HCI_CONN_PA_SYNC, &c->flags)) continue; if (c->iso_qos.bcast.big == big) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn * hci_conn_hash_lookup_pa_sync_handle(struct hci_dev *hdev, __u16 sync_handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != ISO_LINK) continue; if (c->sync_handle == sync_handle) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev, __u8 type, __u16 state) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->state == state) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } typedef void (*hci_conn_func_t)(struct hci_conn *conn, void *data); static inline void hci_conn_hash_list_state(struct hci_dev *hdev, hci_conn_func_t func, __u8 type, __u16 state, void *data) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; if (!func) return; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->state == state) func(c, data); } rcu_read_unlock(); } static inline void hci_conn_hash_list_flag(struct hci_dev *hdev, hci_conn_func_t func, __u8 type, __u8 flag, void *data) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; if (!func) return; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && test_bit(flag, &c->flags)) func(c, data); } rcu_read_unlock(); } static inline struct hci_conn *hci_lookup_le_connect(struct hci_dev *hdev) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == LE_LINK && c->state == BT_CONNECT && !test_bit(HCI_CONN_SCANNING, &c->flags)) { rcu_read_unlock(); return c; } } rcu_read_unlock(); return NULL; } /* Returns true if an le connection is in the scanning state */ static inline bool hci_is_le_conn_scanning(struct hci_dev *hdev) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type == LE_LINK && c->state == BT_CONNECT && test_bit(HCI_CONN_SCANNING, &c->flags)) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } int hci_disconnect(struct hci_conn *conn, __u8 reason); bool hci_setup_sync(struct hci_conn *conn, __u16 handle); void hci_sco_setup(struct hci_conn *conn, __u8 status); bool hci_iso_setup_path(struct hci_conn *conn); int hci_le_create_cis_pending(struct hci_dev *hdev); int hci_conn_check_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role, u16 handle); struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role); void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); struct hci_chan *hci_chan_create(struct hci_conn *conn); void hci_chan_del(struct hci_chan *chan); void hci_chan_list_flush(struct hci_conn *conn); struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle); struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, u16 conn_timeout, enum conn_reasons conn_reason); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, u16 conn_timeout, u8 role, u8 phy, u8 sec_phy); void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, enum conn_reasons conn_reason, u16 timeout); struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, __u16 setting, struct bt_codec *codec, u16 timeout); struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos); struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, struct bt_iso_qos *qos, __u8 base_len, __u8 *base); struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos); struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos, __u8 data_len, __u8 *data); struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, __u8 sid, struct bt_iso_qos *qos); int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, struct bt_iso_qos *qos, __u16 sync_handle, __u8 num_bis, __u8 bis[]); int hci_conn_check_link_mode(struct hci_conn *conn); int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level); int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type, bool initiator); int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); void hci_conn_failed(struct hci_conn *conn, u8 status); u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle); /* * hci_conn_get() and hci_conn_put() are used to control the life-time of an * "hci_conn" object. They do not guarantee that the hci_conn object is running, * working or anything else. They just guarantee that the object is available * and can be dereferenced. So you can use its locks, local variables and any * other constant data. * Before accessing runtime data, you _must_ lock the object and then check that * it is still running. As soon as you release the locks, the connection might * get dropped, though. * * On the other hand, hci_conn_hold() and hci_conn_drop() are used to control * how long the underlying connection is held. So every channel that runs on the * hci_conn object calls this to prevent the connection from disappearing. As * long as you hold a device, you must also guarantee that you have a valid * reference to the device via hci_conn_get() (or the initial reference from * hci_conn_add()). * The hold()/drop() ref-count is known to drop below 0 sometimes, which doesn't * break because nobody cares for that. But this means, we cannot use * _get()/_drop() in it, but require the caller to have a valid ref (FIXME). */ static inline struct hci_conn *hci_conn_get(struct hci_conn *conn) { get_device(&conn->dev); return conn; } static inline void hci_conn_put(struct hci_conn *conn) { put_device(&conn->dev); } static inline struct hci_conn *hci_conn_hold(struct hci_conn *conn) { BT_DBG("hcon %p orig refcnt %d", conn, atomic_read(&conn->refcnt)); atomic_inc(&conn->refcnt); cancel_delayed_work(&conn->disc_work); return conn; } static inline void hci_conn_drop(struct hci_conn *conn) { BT_DBG("hcon %p orig refcnt %d", conn, atomic_read(&conn->refcnt)); if (atomic_dec_and_test(&conn->refcnt)) { unsigned long timeo; switch (conn->type) { case ACL_LINK: case LE_LINK: cancel_delayed_work(&conn->idle_work); if (conn->state == BT_CONNECTED) { timeo = conn->disc_timeout; if (!conn->out) timeo *= 2; } else { timeo = 0; } break; default: timeo = 0; break; } cancel_delayed_work(&conn->disc_work); queue_delayed_work(conn->hdev->workqueue, &conn->disc_work, timeo); } } /* ----- HCI Devices ----- */ static inline void hci_dev_put(struct hci_dev *d) { BT_DBG("%s orig refcnt %d", d->name, kref_read(&d->dev.kobj.kref)); put_device(&d->dev); } static inline struct hci_dev *hci_dev_hold(struct hci_dev *d) { BT_DBG("%s orig refcnt %d", d->name, kref_read(&d->dev.kobj.kref)); get_device(&d->dev); return d; } #define hci_dev_lock(d) mutex_lock(&d->lock) #define hci_dev_unlock(d) mutex_unlock(&d->lock) #define to_hci_dev(d) container_of(d, struct hci_dev, dev) #define to_hci_conn(c) container_of(c, struct hci_conn, dev) static inline void *hci_get_drvdata(struct hci_dev *hdev) { return dev_get_drvdata(&hdev->dev); } static inline void hci_set_drvdata(struct hci_dev *hdev, void *data) { dev_set_drvdata(&hdev->dev, data); } static inline void *hci_get_priv(struct hci_dev *hdev) { return (char *)hdev + sizeof(*hdev); } struct hci_dev *hci_dev_get(int index); struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, u8 src_type); struct hci_dev *hci_alloc_dev_priv(int sizeof_priv); static inline struct hci_dev *hci_alloc_dev(void) { return hci_alloc_dev_priv(0); } void hci_free_dev(struct hci_dev *hdev); int hci_register_dev(struct hci_dev *hdev); void hci_unregister_dev(struct hci_dev *hdev); void hci_release_dev(struct hci_dev *hdev); int hci_register_suspend_notifier(struct hci_dev *hdev); int hci_unregister_suspend_notifier(struct hci_dev *hdev); int hci_suspend_dev(struct hci_dev *hdev); int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); __printf(2, 3) void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...); __printf(2, 3) void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...); static inline void hci_set_msft_opcode(struct hci_dev *hdev, __u16 opcode) { #if IS_ENABLED(CONFIG_BT_MSFTEXT) hdev->msft_opcode = opcode; #endif } static inline void hci_set_aosp_capable(struct hci_dev *hdev) { #if IS_ENABLED(CONFIG_BT_AOSPEXT) hdev->aosp_capable = true; #endif } static inline void hci_devcd_setup(struct hci_dev *hdev) { #ifdef CONFIG_DEV_COREDUMP INIT_WORK(&hdev->dump.dump_rx, hci_devcd_rx); INIT_DELAYED_WORK(&hdev->dump.dump_timeout, hci_devcd_timeout); skb_queue_head_init(&hdev->dump.dump_q); #endif } int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); int hci_dev_do_close(struct hci_dev *hdev); int hci_dev_reset(__u16 dev); int hci_dev_reset_stat(__u16 dev); int hci_dev_cmd(unsigned int cmd, void __user *arg); int hci_get_dev_list(void __user *arg); int hci_get_dev_info(void __user *arg); int hci_get_conn_list(void __user *arg); int hci_get_conn_info(struct hci_dev *hdev, void __user *arg); int hci_get_auth_info(struct hci_dev *hdev, void __user *arg); int hci_inquiry(void __user *arg); struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *list, bdaddr_t *bdaddr, u8 type); struct bdaddr_list_with_irk *hci_bdaddr_list_lookup_with_irk( struct list_head *list, bdaddr_t *bdaddr, u8 type); struct bdaddr_list_with_flags * hci_bdaddr_list_lookup_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_add(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_add_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type, u8 *peer_irk, u8 *local_irk); int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type, u32 flags); int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type); int hci_bdaddr_list_del_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type); void hci_bdaddr_list_clear(struct list_head *list); struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_clear_disabled(struct hci_dev *hdev); void hci_conn_params_free(struct hci_conn_params *param); void hci_pend_le_list_del_init(struct hci_conn_params *param); void hci_pend_le_list_add(struct hci_conn_params *param, struct list_head *list); struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type); void hci_uuids_clear(struct hci_dev *hdev); void hci_link_keys_clear(struct hci_dev *hdev); struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr); struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len, bool *persistent); struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type, u8 authenticated, u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand); struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 role); int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); void hci_smp_ltks_clear(struct hci_dev *hdev); int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr); struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa); struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type); struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 val[16], bdaddr_t *rpa); void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type); bool hci_is_blocked_key(struct hci_dev *hdev, u8 type, u8 val[16]); void hci_blocked_keys_clear(struct hci_dev *hdev); void hci_smp_irks_clear(struct hci_dev *hdev); bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type); void hci_remote_oob_data_clear(struct hci_dev *hdev); struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 *hash192, u8 *rand192, u8 *hash256, u8 *rand256); int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); void hci_adv_instances_clear(struct hci_dev *hdev); struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance); struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance); struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data, u16 timeout, u16 duration, s8 tx_power, u32 min_interval, u32 max_interval, u8 mesh_handle); struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u32 flags, u8 data_len, u8 *data, u32 min_interval, u32 max_interval); int hci_set_adv_instance_data(struct hci_dev *hdev, u8 instance, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data); int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired); u32 hci_adv_instance_flags(struct hci_dev *hdev, u8 instance); bool hci_adv_instance_is_scannable(struct hci_dev *hdev, u8 instance); void hci_adv_monitors_clear(struct hci_dev *hdev); void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor); int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor); int hci_remove_single_adv_monitor(struct hci_dev *hdev, u16 handle); int hci_remove_all_adv_monitor(struct hci_dev *hdev); bool hci_is_adv_monitoring(struct hci_dev *hdev); int hci_get_adv_monitor_offload_ext(struct hci_dev *hdev); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); void hci_init_sysfs(struct hci_dev *hdev); void hci_conn_init_sysfs(struct hci_conn *conn); void hci_conn_add_sysfs(struct hci_conn *conn); void hci_conn_del_sysfs(struct hci_conn *conn); #define SET_HCIDEV_DEV(hdev, pdev) ((hdev)->dev.parent = (pdev)) #define GET_HCIDEV_DEV(hdev) ((hdev)->dev.parent) /* ----- LMP capabilities ----- */ #define lmp_encrypt_capable(dev) ((dev)->features[0][0] & LMP_ENCRYPT) #define lmp_rswitch_capable(dev) ((dev)->features[0][0] & LMP_RSWITCH) #define lmp_hold_capable(dev) ((dev)->features[0][0] & LMP_HOLD) #define lmp_sniff_capable(dev) ((dev)->features[0][0] & LMP_SNIFF) #define lmp_park_capable(dev) ((dev)->features[0][1] & LMP_PARK) #define lmp_inq_rssi_capable(dev) ((dev)->features[0][3] & LMP_RSSI_INQ) #define lmp_esco_capable(dev) ((dev)->features[0][3] & LMP_ESCO) #define lmp_bredr_capable(dev) (!((dev)->features[0][4] & LMP_NO_BREDR)) #define lmp_le_capable(dev) ((dev)->features[0][4] & LMP_LE) #define lmp_sniffsubr_capable(dev) ((dev)->features[0][5] & LMP_SNIFF_SUBR) #define lmp_pause_enc_capable(dev) ((dev)->features[0][5] & LMP_PAUSE_ENC) #define lmp_esco_2m_capable(dev) ((dev)->features[0][5] & LMP_EDR_ESCO_2M) #define lmp_ext_inq_capable(dev) ((dev)->features[0][6] & LMP_EXT_INQ) #define lmp_le_br_capable(dev) (!!((dev)->features[0][6] & LMP_SIMUL_LE_BR)) #define lmp_ssp_capable(dev) ((dev)->features[0][6] & LMP_SIMPLE_PAIR) #define lmp_no_flush_capable(dev) ((dev)->features[0][6] & LMP_NO_FLUSH) #define lmp_lsto_capable(dev) ((dev)->features[0][7] & LMP_LSTO) #define lmp_inq_tx_pwr_capable(dev) ((dev)->features[0][7] & LMP_INQ_TX_PWR) #define lmp_ext_feat_capable(dev) ((dev)->features[0][7] & LMP_EXTFEATURES) #define lmp_transp_capable(dev) ((dev)->features[0][2] & LMP_TRANSPARENT) #define lmp_edr_2m_capable(dev) ((dev)->features[0][3] & LMP_EDR_2M) #define lmp_edr_3m_capable(dev) ((dev)->features[0][3] & LMP_EDR_3M) #define lmp_edr_3slot_capable(dev) ((dev)->features[0][4] & LMP_EDR_3SLOT) #define lmp_edr_5slot_capable(dev) ((dev)->features[0][5] & LMP_EDR_5SLOT) /* ----- Extended LMP capabilities ----- */ #define lmp_cpb_central_capable(dev) ((dev)->features[2][0] & LMP_CPB_CENTRAL) #define lmp_cpb_peripheral_capable(dev) ((dev)->features[2][0] & LMP_CPB_PERIPHERAL) #define lmp_sync_train_capable(dev) ((dev)->features[2][0] & LMP_SYNC_TRAIN) #define lmp_sync_scan_capable(dev) ((dev)->features[2][0] & LMP_SYNC_SCAN) #define lmp_sc_capable(dev) ((dev)->features[2][1] & LMP_SC) #define lmp_ping_capable(dev) ((dev)->features[2][1] & LMP_PING) /* ----- Host capabilities ----- */ #define lmp_host_ssp_capable(dev) ((dev)->features[1][0] & LMP_HOST_SSP) #define lmp_host_sc_capable(dev) ((dev)->features[1][0] & LMP_HOST_SC) #define lmp_host_le_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE)) #define lmp_host_le_br_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE_BREDR)) #define hdev_is_powered(dev) (test_bit(HCI_UP, &(dev)->flags) && \ !hci_dev_test_flag(dev, HCI_AUTO_OFF)) #define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ hci_dev_test_flag(dev, HCI_SC_ENABLED)) #define rpa_valid(dev) (bacmp(&dev->rpa, BDADDR_ANY) && \ !hci_dev_test_flag(dev, HCI_RPA_EXPIRED)) #define adv_rpa_valid(adv) (bacmp(&adv->random_addr, BDADDR_ANY) && \ !adv->rpa_expired) #define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M)) #define le_2m_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_2M)) #define scan_2m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_2M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_2M)) #define le_coded_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_CODED) && \ !test_bit(HCI_QUIRK_BROKEN_LE_CODED, \ &(dev)->quirks)) #define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) /* Use LL Privacy based address resolution if supported */ #define use_ll_privacy(dev) (ll_privacy_capable(dev) && \ hci_dev_test_flag(dev, HCI_ENABLE_LL_PRIVACY)) #define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ (hdev->commands[39] & 0x04)) #define read_key_size_capable(dev) \ ((dev)->commands[20] & 0x10 && \ !test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) /* Use enhanced synchronous connection if command is supported and its quirk * has not been set. */ #define enhanced_sync_conn_capable(dev) \ (((dev)->commands[29] & 0x08) && \ !test_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &(dev)->quirks)) /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ ((dev)->commands[37] & 0x40) && \ !test_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &(dev)->quirks)) /* Use ext create connection if command is supported */ #define use_ext_conn(dev) ((dev)->commands[37] & 0x80) /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) /* Maximum advertising length */ #define max_adv_len(dev) \ (ext_adv_capable(dev) ? HCI_MAX_EXT_AD_LENGTH : HCI_MAX_AD_LENGTH) /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 1789: * * C24: Mandatory if the LE Controller supports Connection State and either * LE Feature (LL Privacy) or LE Feature (Extended Advertising) is supported */ #define use_enhanced_conn_complete(dev) (ll_privacy_capable(dev) || \ ext_adv_capable(dev)) /* Periodic advertising support */ #define per_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_PERIODIC_ADV)) /* CIS Master/Slave and BIS support */ #define iso_capable(dev) (cis_capable(dev) || bis_capable(dev)) #define cis_capable(dev) \ (cis_central_capable(dev) || cis_peripheral_capable(dev)) #define cis_central_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_CENTRAL) #define cis_peripheral_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL) #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER) #define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ (!test_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &(dev)->quirks))) /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 static inline int hci_proto_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 type, __u8 *flags) { switch (type) { case ACL_LINK: return l2cap_connect_ind(hdev, bdaddr); case SCO_LINK: case ESCO_LINK: return sco_connect_ind(hdev, bdaddr, flags); case ISO_LINK: return iso_connect_ind(hdev, bdaddr, flags); default: BT_ERR("unknown link type %d", type); return -EINVAL; } } static inline int hci_proto_disconn_ind(struct hci_conn *conn) { if (conn->type != ACL_LINK && conn->type != LE_LINK) return HCI_ERROR_REMOTE_USER_TERM; return l2cap_disconn_ind(conn); } /* ----- HCI callbacks ----- */ struct hci_cb { struct list_head list; char *name; void (*connect_cfm) (struct hci_conn *conn, __u8 status); void (*disconn_cfm) (struct hci_conn *conn, __u8 status); void (*security_cfm) (struct hci_conn *conn, __u8 status, __u8 encrypt); void (*key_change_cfm) (struct hci_conn *conn, __u8 status); void (*role_switch_cfm) (struct hci_conn *conn, __u8 status, __u8 role); }; static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->connect_cfm) cb->connect_cfm(conn, status); } mutex_unlock(&hci_cb_list_lock); if (conn->connect_cfm_cb) conn->connect_cfm_cb(conn, status); } static inline void hci_disconn_cfm(struct hci_conn *conn, __u8 reason) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->disconn_cfm) cb->disconn_cfm(conn, reason); } mutex_unlock(&hci_cb_list_lock); if (conn->disconn_cfm_cb) conn->disconn_cfm_cb(conn, reason); } static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; __u8 encrypt; if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) return; encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } mutex_unlock(&hci_cb_list_lock); if (conn->security_cfm_cb) conn->security_cfm_cb(conn, status); } static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; __u8 encrypt; if (conn->state == BT_CONFIG) { if (!status) conn->state = BT_CONNECTED; hci_connect_cfm(conn, status); hci_conn_drop(conn); return; } if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) encrypt = 0x00; else if (test_bit(HCI_CONN_AES_CCM, &conn->flags)) encrypt = 0x02; else encrypt = 0x01; if (!status) { if (conn->sec_level == BT_SECURITY_SDP) conn->sec_level = BT_SECURITY_LOW; if (conn->pending_sec_level > conn->sec_level) conn->sec_level = conn->pending_sec_level; } mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } mutex_unlock(&hci_cb_list_lock); if (conn->security_cfm_cb) conn->security_cfm_cb(conn, status); } static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->key_change_cfm) cb->key_change_cfm(conn, status); } mutex_unlock(&hci_cb_list_lock); } static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, __u8 role) { struct hci_cb *cb; mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->role_switch_cfm) cb->role_switch_cfm(conn, status, role); } mutex_unlock(&hci_cb_list_lock); } static inline bool hci_bdaddr_is_rpa(bdaddr_t *bdaddr, u8 addr_type) { if (addr_type != ADDR_LE_DEV_RANDOM) return false; if ((bdaddr->b[5] & 0xc0) == 0x40) return true; return false; } static inline bool hci_is_identity_address(bdaddr_t *addr, u8 addr_type) { if (addr_type == ADDR_LE_DEV_PUBLIC) return true; /* Check for Random Static address type */ if ((addr->b[5] & 0xc0) == 0xc0) return true; return false; } static inline struct smp_irk *hci_get_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { if (!hci_bdaddr_is_rpa(bdaddr, addr_type)) return NULL; return hci_find_irk_by_rpa(hdev, bdaddr); } static inline int hci_check_conn_params(u16 min, u16 max, u16 latency, u16 to_multiplier) { u16 max_latency; if (min > max) { BT_WARN("min %d > max %d", min, max); return -EINVAL; } if (min < 6) { BT_WARN("min %d < 6", min); return -EINVAL; } if (max > 3200) { BT_WARN("max %d > 3200", max); return -EINVAL; } if (to_multiplier < 10) { BT_WARN("to_multiplier %d < 10", to_multiplier); return -EINVAL; } if (to_multiplier > 3200) { BT_WARN("to_multiplier %d > 3200", to_multiplier); return -EINVAL; } if (max >= to_multiplier * 8) { BT_WARN("max %d >= to_multiplier %d * 8", max, to_multiplier); return -EINVAL; } max_latency = (to_multiplier * 4 / max) - 1; if (latency > 499) { BT_WARN("latency %d > 499", latency); return -EINVAL; } if (latency > max_latency) { BT_WARN("latency %d > max_latency %d", latency, max_latency); return -EINVAL; } return 0; } int hci_register_cb(struct hci_cb *hcb); int hci_unregister_cb(struct hci_cb *hcb); int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param); int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, const void *param); void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags); void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); void hci_send_iso(struct hci_conn *conn, struct sk_buff *skb); void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); void *hci_recv_event_data(struct hci_dev *hdev, __u8 event); u32 hci_conn_get_phy(struct hci_conn *conn); /* ----- HCI Sockets ----- */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, int flag, struct sock *skip_sk); void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event, void *data, u16 data_len, ktime_t tstamp, int flag, struct sock *skip_sk); void hci_sock_dev_event(struct hci_dev *hdev, int event); #define HCI_MGMT_VAR_LEN BIT(0) #define HCI_MGMT_NO_HDEV BIT(1) #define HCI_MGMT_UNTRUSTED BIT(2) #define HCI_MGMT_UNCONFIGURED BIT(3) #define HCI_MGMT_HDEV_OPTIONAL BIT(4) struct hci_mgmt_handler { int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, u16 data_len); size_t data_len; unsigned long flags; }; struct hci_mgmt_chan { struct list_head list; unsigned short channel; size_t handler_count; const struct hci_mgmt_handler *handlers; void (*hdev_init) (struct sock *sk, struct hci_dev *hdev); }; int hci_mgmt_chan_register(struct hci_mgmt_chan *c); void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); /* Management interface */ #define DISCOV_TYPE_BREDR (BIT(BDADDR_BREDR)) #define DISCOV_TYPE_LE (BIT(BDADDR_LE_PUBLIC) | \ BIT(BDADDR_LE_RANDOM)) #define DISCOV_TYPE_INTERLEAVED (BIT(BDADDR_BREDR) | \ BIT(BDADDR_LE_PUBLIC) | \ BIT(BDADDR_LE_RANDOM)) /* These LE scan and inquiry parameters were chosen according to LE General * Discovery Procedure specification. */ #define DISCOV_LE_SCAN_WIN 0x0012 /* 11.25 msec */ #define DISCOV_LE_SCAN_INT 0x0012 /* 11.25 msec */ #define DISCOV_LE_SCAN_INT_FAST 0x0060 /* 60 msec */ #define DISCOV_LE_SCAN_WIN_FAST 0x0030 /* 30 msec */ #define DISCOV_LE_SCAN_INT_CONN 0x0060 /* 60 msec */ #define DISCOV_LE_SCAN_WIN_CONN 0x0060 /* 60 msec */ #define DISCOV_LE_SCAN_INT_SLOW1 0x0800 /* 1.28 sec */ #define DISCOV_LE_SCAN_WIN_SLOW1 0x0012 /* 11.25 msec */ #define DISCOV_LE_SCAN_INT_SLOW2 0x1000 /* 2.56 sec */ #define DISCOV_LE_SCAN_WIN_SLOW2 0x0024 /* 22.5 msec */ #define DISCOV_CODED_SCAN_INT_FAST 0x0120 /* 180 msec */ #define DISCOV_CODED_SCAN_WIN_FAST 0x0090 /* 90 msec */ #define DISCOV_CODED_SCAN_INT_SLOW1 0x1800 /* 3.84 sec */ #define DISCOV_CODED_SCAN_WIN_SLOW1 0x0036 /* 33.75 msec */ #define DISCOV_CODED_SCAN_INT_SLOW2 0x3000 /* 7.68 sec */ #define DISCOV_CODED_SCAN_WIN_SLOW2 0x006c /* 67.5 msec */ #define DISCOV_LE_TIMEOUT 10240 /* msec */ #define DISCOV_INTERLEAVED_TIMEOUT 5120 /* msec */ #define DISCOV_INTERLEAVED_INQUIRY_LEN 0x04 #define DISCOV_BREDR_INQUIRY_LEN 0x08 #define DISCOV_LE_RESTART_DELAY msecs_to_jiffies(200) /* msec */ #define DISCOV_LE_FAST_ADV_INT_MIN 0x00A0 /* 100 msec */ #define DISCOV_LE_FAST_ADV_INT_MAX 0x00F0 /* 150 msec */ #define DISCOV_LE_PER_ADV_INT_MIN 0x00A0 /* 200 msec */ #define DISCOV_LE_PER_ADV_INT_MAX 0x00A0 /* 200 msec */ #define DISCOV_LE_ADV_MESH_MIN 0x00A0 /* 100 msec */ #define DISCOV_LE_ADV_MESH_MAX 0x00A0 /* 100 msec */ #define INTERVAL_TO_MS(x) (((x) * 10) / 0x10) #define NAME_RESOLVE_DURATION msecs_to_jiffies(10240) /* 10.24 sec */ void mgmt_fill_version_info(void *ver); int mgmt_new_settings(struct hci_dev *hdev); void mgmt_index_added(struct hci_dev *hdev); void mgmt_index_removed(struct hci_dev *hdev); void mgmt_set_powered_failed(struct hci_dev *hdev, int err); void mgmt_power_on(struct hci_dev *hdev, int err); void __mgmt_power_off(struct hci_dev *hdev); void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent); void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, u8 *name, u8 name_len); void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 reason, bool mgmt_connected); void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure); void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status); void mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 status); int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u32 value, u8 confirm_hint); int mgmt_user_confirm_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_confirm_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_passkey_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type); int mgmt_user_passkey_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_passkey_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status); int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u32 passkey, u8 entered); void mgmt_auth_failed(struct hci_conn *conn, u8 status); void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status); void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, u8 status); void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status); void mgmt_start_discovery_complete(struct hci_dev *hdev, u8 status); void mgmt_stop_discovery_complete(struct hci_dev *hdev, u8 status); void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len, u64 instant); void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, s8 rssi, u8 *name, u8 name_len); void mgmt_discovering(struct hci_dev *hdev, u8 discovering); void mgmt_suspending(struct hci_dev *hdev, u8 state); void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr, u8 addr_type); bool mgmt_powering_down(struct hci_dev *hdev); void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent); void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent); void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, bool persistent); void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 store_hint, u16 min_interval, u16 max_interval, u16 latency, u16 timeout); void mgmt_smp_complete(struct hci_conn *conn, bool complete); bool mgmt_get_connectable(struct hci_dev *hdev); u8 mgmt_get_adv_discov_flags(struct hci_dev *hdev); void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, u8 instance); void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev, u8 instance); void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle); int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, bdaddr_t *bdaddr, u8 addr_type); int hci_abort_conn(struct hci_conn *conn, u8 reason); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, __u8 ltk[16], __u8 key_size); void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *bdaddr_type); #define SCO_AIRMODE_MASK 0x0003 #define SCO_AIRMODE_CVSD 0x0000 #define SCO_AIRMODE_TRANSP 0x0003 #define LOCAL_CODEC_ACL_MASK BIT(0) #define LOCAL_CODEC_SCO_MASK BIT(1) #define TRANSPORT_TYPE_MAX 0x04 #endif /* __HCI_CORE_H */ |
| 326 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_PGALLOC_H #define __ASM_GENERIC_PGALLOC_H #ifdef CONFIG_MMU #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) /** * __pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * This function is intended for architectures that need * anything beyond simple page allocation. * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm) { struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL & ~__GFP_HIGHMEM, 0); if (!ptdesc) return NULL; return ptdesc_address(ptdesc); } #define __pte_alloc_one_kernel(...) alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** * pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm) { return __pte_alloc_one_kernel_noprof(mm); } #define pte_alloc_one_kernel(...) alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__)) #endif /** * pte_free_kernel - free PTE-level kernel page table memory * @mm: the mm_struct of the current context * @pte: pointer to the memory containing the page table */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { pagetable_free(virt_to_ptdesc(pte)); } /** * __pte_alloc_one - allocate memory for a PTE-level user page table * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. * * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp) { struct ptdesc *ptdesc; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pte_ctor(ptdesc)) { pagetable_free(ptdesc); return NULL; } return ptdesc_page(ptdesc); } #define __pte_alloc_one(...) alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE /** * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm) { return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER); } #define pte_alloc_one(...) alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__)) #endif /* * Should really implement gc for free page table pages. This could be * done with a reference count in struct page. */ /** * pte_free - free PTE-level user page table memory * @mm: the mm_struct of the current context * @pte_page: the `struct page` referencing the ptdesc */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { struct ptdesc *ptdesc = page_ptdesc(pte_page); pagetable_pte_dtor(ptdesc); pagetable_free(ptdesc); } #if CONFIG_PGTABLE_LEVELS > 2 #ifndef __HAVE_ARCH_PMD_ALLOC_ONE /** * pmd_alloc_one - allocate memory for a PMD-level page table * @mm: the mm_struct of the current context * * Allocate memory for a page table and ptdesc and runs pagetable_pmd_ctor(). * * Allocations use %GFP_PGTABLE_USER in user context and * %GFP_PGTABLE_KERNEL in kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { struct ptdesc *ptdesc; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pmd_ctor(ptdesc)) { pagetable_free(ptdesc); return NULL; } return ptdesc_address(ptdesc); } #define pmd_alloc_one(...) alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__)) #endif #ifndef __HAVE_ARCH_PMD_FREE static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { struct ptdesc *ptdesc = virt_to_ptdesc(pmd); BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); pagetable_pmd_dtor(ptdesc); pagetable_free(ptdesc); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; gfp &= ~__GFP_HIGHMEM; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; pagetable_pud_ctor(ptdesc); return ptdesc_address(ptdesc); } #define __pud_alloc_one(...) alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** * pud_alloc_one - allocate memory for a PUD-level page table * @mm: the mm_struct of the current context * * Allocate memory for a page table using %GFP_PGTABLE_USER for user context * and %GFP_PGTABLE_KERNEL for kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { return __pud_alloc_one_noprof(mm, addr); } #define pud_alloc_one(...) alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__)) #endif static inline void __pud_free(struct mm_struct *mm, pud_t *pud) { struct ptdesc *ptdesc = virt_to_ptdesc(pud); BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); pagetable_pud_dtor(ptdesc); pagetable_free(ptdesc); } #ifndef __HAVE_ARCH_PUD_FREE static inline void pud_free(struct mm_struct *mm, pud_t *pud) { __pud_free(mm, pud); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { pagetable_free(virt_to_ptdesc(pgd)); } #endif #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_OPTS_H #define _BCACHEFS_OPTS_H #include <linux/bug.h> #include <linux/log2.h> #include <linux/string.h> #include <linux/sysfs.h> #include "bcachefs_format.h" struct bch_fs; extern const char * const bch2_error_actions[]; extern const char * const bch2_fsck_fix_opts[]; extern const char * const bch2_version_upgrade_opts[]; extern const char * const bch2_sb_features[]; extern const char * const bch2_sb_compat[]; extern const char * const __bch2_btree_ids[]; extern const char * const bch2_csum_opts[]; extern const char * const bch2_compression_opts[]; extern const char * const bch2_str_hash_types[]; extern const char * const bch2_str_hash_opts[]; extern const char * const __bch2_data_types[]; extern const char * const bch2_member_states[]; extern const char * const bch2_d_types[]; void bch2_prt_jset_entry_type(struct printbuf *, enum bch_jset_entry_type); void bch2_prt_fs_usage_type(struct printbuf *, enum bch_fs_usage_type); void bch2_prt_data_type(struct printbuf *, enum bch_data_type); void bch2_prt_csum_type(struct printbuf *, enum bch_csum_type); void bch2_prt_compression_type(struct printbuf *, enum bch_compression_type); static inline const char *bch2_d_type_str(unsigned d_type) { return (d_type < BCH_DT_MAX ? bch2_d_types[d_type] : NULL) ?: "(bad d_type)"; } /* * Mount options; we also store defaults in the superblock. * * Also exposed via sysfs: if an option is writeable, and it's also stored in * the superblock, changing it via sysfs (currently? might change this) also * updates the superblock. * * We store options as signed integers, where -1 means undefined. This means we * can pass the mount options to bch2_fs_alloc() as a whole struct, and then only * apply the options from that struct that are defined. */ /* dummy option, for options that aren't stored in the superblock */ u64 BCH2_NO_SB_OPT(const struct bch_sb *); void SET_BCH2_NO_SB_OPT(struct bch_sb *, u64); /* When can be set: */ enum opt_flags { OPT_FS = (1 << 0), /* Filesystem option */ OPT_DEVICE = (1 << 1), /* Device option */ OPT_INODE = (1 << 2), /* Inode option */ OPT_FORMAT = (1 << 3), /* May be specified at format time */ OPT_MOUNT = (1 << 4), /* May be specified at mount time */ OPT_RUNTIME = (1 << 5), /* May be specified at runtime */ OPT_HUMAN_READABLE = (1 << 6), OPT_MUST_BE_POW_2 = (1 << 7), /* Must be power of 2 */ OPT_SB_FIELD_SECTORS = (1 << 8),/* Superblock field is >> 9 of actual value */ OPT_SB_FIELD_ILOG2 = (1 << 9), /* Superblock field is ilog2 of actual value */ OPT_HIDDEN = (1 << 10), }; enum opt_type { BCH_OPT_BOOL, BCH_OPT_UINT, BCH_OPT_STR, BCH_OPT_FN, }; struct bch_opt_fn { int (*parse)(struct bch_fs *, const char *, u64 *, struct printbuf *); void (*to_text)(struct printbuf *, struct bch_fs *, struct bch_sb *, u64); int (*validate)(u64, struct printbuf *); }; /** * x(name, shortopt, type, in mem type, mode, sb_opt) * * @name - name of mount option, sysfs attribute, and struct bch_opts * member * * @mode - when opt may be set * * @sb_option - name of corresponding superblock option * * @type - one of OPT_BOOL, OPT_UINT, OPT_STR */ /* * XXX: add fields for * - default value * - helptext */ #ifdef __KERNEL__ #define RATELIMIT_ERRORS_DEFAULT true #else #define RATELIMIT_ERRORS_DEFAULT false #endif #ifdef CONFIG_BCACHEFS_DEBUG #define BCACHEFS_VERBOSE_DEFAULT true #else #define BCACHEFS_VERBOSE_DEFAULT false #endif #define BCH_FIX_ERRORS_OPTS() \ x(exit, 0) \ x(yes, 1) \ x(no, 2) \ x(ask, 3) enum fsck_err_opts { #define x(t, n) FSCK_FIX_##t, BCH_FIX_ERRORS_OPTS() #undef x }; #define BCH_OPTS() \ x(block_size, u16, \ OPT_FS|OPT_FORMAT| \ OPT_HUMAN_READABLE|OPT_MUST_BE_POW_2|OPT_SB_FIELD_SECTORS, \ OPT_UINT(512, 1U << 16), \ BCH_SB_BLOCK_SIZE, 8, \ "size", NULL) \ x(btree_node_size, u32, \ OPT_FS|OPT_FORMAT| \ OPT_HUMAN_READABLE|OPT_MUST_BE_POW_2|OPT_SB_FIELD_SECTORS, \ OPT_UINT(512, 1U << 20), \ BCH_SB_BTREE_NODE_SIZE, 512, \ "size", "Btree node size, default 256k") \ x(errors, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_STR(bch2_error_actions), \ BCH_SB_ERROR_ACTION, BCH_ON_ERROR_fix_safe, \ NULL, "Action to take on filesystem error") \ x(metadata_replicas, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_UINT(1, BCH_REPLICAS_MAX), \ BCH_SB_META_REPLICAS_WANT, 1, \ "#", "Number of metadata replicas") \ x(data_replicas, u8, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_UINT(1, BCH_REPLICAS_MAX), \ BCH_SB_DATA_REPLICAS_WANT, 1, \ "#", "Number of data replicas") \ x(metadata_replicas_required, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT, \ OPT_UINT(1, BCH_REPLICAS_MAX), \ BCH_SB_META_REPLICAS_REQ, 1, \ "#", NULL) \ x(data_replicas_required, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT, \ OPT_UINT(1, BCH_REPLICAS_MAX), \ BCH_SB_DATA_REPLICAS_REQ, 1, \ "#", NULL) \ x(encoded_extent_max, u32, \ OPT_FS|OPT_FORMAT| \ OPT_HUMAN_READABLE|OPT_MUST_BE_POW_2|OPT_SB_FIELD_SECTORS|OPT_SB_FIELD_ILOG2,\ OPT_UINT(4096, 2U << 20), \ BCH_SB_ENCODED_EXTENT_MAX_BITS, 64 << 10, \ "size", "Maximum size of checksummed/compressed extents")\ x(metadata_checksum, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_STR(bch2_csum_opts), \ BCH_SB_META_CSUM_TYPE, BCH_CSUM_OPT_crc32c, \ NULL, NULL) \ x(data_checksum, u8, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_STR(bch2_csum_opts), \ BCH_SB_DATA_CSUM_TYPE, BCH_CSUM_OPT_crc32c, \ NULL, NULL) \ x(compression, u8, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_FN(bch2_opt_compression), \ BCH_SB_COMPRESSION_TYPE, BCH_COMPRESSION_OPT_none, \ NULL, NULL) \ x(background_compression, u8, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_FN(bch2_opt_compression), \ BCH_SB_BACKGROUND_COMPRESSION_TYPE,BCH_COMPRESSION_OPT_none, \ NULL, NULL) \ x(str_hash, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_STR(bch2_str_hash_opts), \ BCH_SB_STR_HASH_TYPE, BCH_STR_HASH_OPT_siphash, \ NULL, "Hash function for directory entries and xattrs")\ x(metadata_target, u16, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_FN(bch2_opt_target), \ BCH_SB_METADATA_TARGET, 0, \ "(target)", "Device or label for metadata writes") \ x(foreground_target, u16, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_FN(bch2_opt_target), \ BCH_SB_FOREGROUND_TARGET, 0, \ "(target)", "Device or label for foreground writes") \ x(background_target, u16, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_FN(bch2_opt_target), \ BCH_SB_BACKGROUND_TARGET, 0, \ "(target)", "Device or label to move data to in the background")\ x(promote_target, u16, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_FN(bch2_opt_target), \ BCH_SB_PROMOTE_TARGET, 0, \ "(target)", "Device or label to promote data to on read") \ x(erasure_code, u16, \ OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH_SB_ERASURE_CODE, false, \ NULL, "Enable erasure coding (DO NOT USE YET)") \ x(inodes_32bit, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH_SB_INODE_32BIT, true, \ NULL, "Constrain inode numbers to 32 bits") \ x(shard_inode_numbers, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH_SB_SHARD_INUMS, true, \ NULL, "Shard new inode numbers by CPU id") \ x(inodes_use_key_cache, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT, \ OPT_BOOL(), \ BCH_SB_INODES_USE_KEY_CACHE, true, \ NULL, "Use the btree key cache for the inodes btree") \ x(btree_node_mem_ptr_optimization, u8, \ OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, true, \ NULL, "Stash pointer to in memory btree node in btree ptr")\ x(gc_reserve_percent, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_UINT(5, 21), \ BCH_SB_GC_RESERVE, 8, \ "%", "Percentage of disk space to reserve for copygc")\ x(gc_reserve_bytes, u64, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME| \ OPT_HUMAN_READABLE|OPT_SB_FIELD_SECTORS, \ OPT_UINT(0, U64_MAX), \ BCH_SB_GC_RESERVE_BYTES, 0, \ "%", "Amount of disk space to reserve for copygc\n" \ "Takes precedence over gc_reserve_percent if set")\ x(root_reserve_percent, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT, \ OPT_UINT(0, 100), \ BCH_SB_ROOT_RESERVE, 0, \ "%", "Percentage of disk space to reserve for superuser")\ x(wide_macs, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH_SB_128_BIT_MACS, false, \ NULL, "Store full 128 bits of cryptographic MACs, instead of 80")\ x(inline_data, u8, \ OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, true, \ NULL, "Enable inline data extents") \ x(acl, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT, \ OPT_BOOL(), \ BCH_SB_POSIX_ACL, true, \ NULL, "Enable POSIX acls") \ x(usrquota, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT, \ OPT_BOOL(), \ BCH_SB_USRQUOTA, false, \ NULL, "Enable user quotas") \ x(grpquota, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT, \ OPT_BOOL(), \ BCH_SB_GRPQUOTA, false, \ NULL, "Enable group quotas") \ x(prjquota, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT, \ OPT_BOOL(), \ BCH_SB_PRJQUOTA, false, \ NULL, "Enable project quotas") \ x(degraded, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Allow mounting in degraded mode") \ x(very_degraded, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Allow mounting in when data will be missing") \ x(no_splitbrain_check, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Don't kick drives out when splitbrain detected")\ x(discard, u8, \ OPT_FS|OPT_MOUNT|OPT_DEVICE, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, true, \ NULL, "Enable discard/TRIM support") \ x(verbose, u8, \ OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, BCACHEFS_VERBOSE_DEFAULT, \ NULL, "Extra debugging information during mount/recovery")\ x(journal_flush_delay, u32, \ OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_UINT(1, U32_MAX), \ BCH_SB_JOURNAL_FLUSH_DELAY, 1000, \ NULL, "Delay in milliseconds before automatic journal commits")\ x(journal_flush_disabled, u8, \ OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH_SB_JOURNAL_FLUSH_DISABLED,false, \ NULL, "Disable journal flush on sync/fsync\n" \ "If enabled, writes can be lost, but only since the\n"\ "last journal write (default 1 second)") \ x(journal_reclaim_delay, u32, \ OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_UINT(0, U32_MAX), \ BCH_SB_JOURNAL_RECLAIM_DELAY, 100, \ NULL, "Delay in milliseconds before automatic journal reclaim")\ x(move_bytes_in_flight, u32, \ OPT_HUMAN_READABLE|OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_UINT(1024, U32_MAX), \ BCH2_NO_SB_OPT, 1U << 20, \ NULL, "Maximum Amount of IO to keep in flight by the move path")\ x(move_ios_in_flight, u32, \ OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_UINT(1, 1024), \ BCH2_NO_SB_OPT, 32, \ NULL, "Maximum number of IOs to keep in flight by the move path")\ x(fsck, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Run fsck on mount") \ x(fsck_memory_usage_percent, u8, \ OPT_FS|OPT_MOUNT, \ OPT_UINT(20, 70), \ BCH2_NO_SB_OPT, 50, \ NULL, "Maximum percentage of system ram fsck is allowed to pin")\ x(fix_errors, u8, \ OPT_FS|OPT_MOUNT, \ OPT_FN(bch2_opt_fix_errors), \ BCH2_NO_SB_OPT, FSCK_FIX_exit, \ NULL, "Fix errors during fsck without asking") \ x(ratelimit_errors, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, RATELIMIT_ERRORS_DEFAULT, \ NULL, "Ratelimit error messages during fsck") \ x(nochanges, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Super read only mode - no writes at all will be issued,\n"\ "even if we have to replay the journal") \ x(norecovery, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Exit recovery immediately prior to journal replay")\ x(recovery_pass_last, u8, \ OPT_FS|OPT_MOUNT, \ OPT_STR_NOLIMIT(bch2_recovery_passes), \ BCH2_NO_SB_OPT, 0, \ NULL, "Exit recovery after specified pass") \ x(retain_recovery_info, u8, \ 0, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Don't free journal entries/keys, scanned btree nodes after startup")\ x(read_entire_journal, u8, \ 0, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Read all journal entries, not just dirty ones")\ x(read_journal_only, u8, \ 0, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Only read the journal, skip the rest of recovery")\ x(journal_transaction_names, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH_SB_JOURNAL_TRANSACTION_NAMES, true, \ NULL, "Log transaction function names in journal") \ x(noexcl, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Don't open device in exclusive mode") \ x(direct_io, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, true, \ NULL, "Use O_DIRECT (userspace only)") \ x(sb, u64, \ OPT_MOUNT, \ OPT_UINT(0, S64_MAX), \ BCH2_NO_SB_OPT, BCH_SB_SECTOR, \ "offset", "Sector offset of superblock") \ x(read_only, u8, \ OPT_FS|OPT_MOUNT|OPT_HIDDEN, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, NULL) \ x(nostart, u8, \ 0, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Don\'t start filesystem, only open devices") \ x(reconstruct_alloc, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Reconstruct alloc btree") \ x(version_upgrade, u8, \ OPT_FS|OPT_MOUNT, \ OPT_STR(bch2_version_upgrade_opts), \ BCH_SB_VERSION_UPGRADE, BCH_VERSION_UPGRADE_compatible, \ NULL, "Set superblock to latest version,\n" \ "allowing any new features to be used") \ x(stdio, u64, \ 0, \ OPT_UINT(0, S64_MAX), \ BCH2_NO_SB_OPT, false, \ NULL, "Pointer to a struct stdio_redirect") \ x(project, u8, \ OPT_INODE, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, NULL) \ x(nocow, u8, \ OPT_FS|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME|OPT_INODE, \ OPT_BOOL(), \ BCH_SB_NOCOW, false, \ NULL, "Nocow mode: Writes will be done in place when possible.\n"\ "Snapshots and reflink will still caused writes to be COW\n"\ "Implicitly disables data checksumming, compression and encryption")\ x(nocow_enabled, u8, \ OPT_FS|OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, true, \ NULL, "Enable nocow mode: enables runtime locking in\n"\ "data move path needed if nocow will ever be in use\n")\ x(no_data_io, u8, \ OPT_MOUNT, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, false, \ NULL, "Skip submit_bio() for data reads and writes, " \ "for performance testing purposes") \ x(fs_size, u64, \ OPT_DEVICE, \ OPT_UINT(0, S64_MAX), \ BCH2_NO_SB_OPT, 0, \ "size", "Size of filesystem on device") \ x(bucket, u32, \ OPT_DEVICE, \ OPT_UINT(0, S64_MAX), \ BCH2_NO_SB_OPT, 0, \ "size", "Size of filesystem on device") \ x(durability, u8, \ OPT_DEVICE, \ OPT_UINT(0, BCH_REPLICAS_MAX), \ BCH2_NO_SB_OPT, 1, \ "n", "Data written to this device will be considered\n"\ "to have already been replicated n times") \ x(btree_node_prefetch, u8, \ OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, true, \ NULL, "BTREE_ITER_prefetch casuse btree nodes to be\n"\ " prefetched sequentially") struct bch_opts { #define x(_name, _bits, ...) unsigned _name##_defined:1; BCH_OPTS() #undef x #define x(_name, _bits, ...) _bits _name; BCH_OPTS() #undef x }; struct bch2_opts_parse { struct bch_opts opts; /* to save opts that can't be parsed before the FS is opened: */ struct printbuf parse_later; }; static const __maybe_unused struct bch_opts bch2_opts_default = { #define x(_name, _bits, _mode, _type, _sb_opt, _default, ...) \ ._name##_defined = true, \ ._name = _default, \ BCH_OPTS() #undef x }; #define opt_defined(_opts, _name) ((_opts)._name##_defined) #define opt_get(_opts, _name) \ (opt_defined(_opts, _name) ? (_opts)._name : bch2_opts_default._name) #define opt_set(_opts, _name, _v) \ do { \ (_opts)._name##_defined = true; \ (_opts)._name = _v; \ } while (0) static inline struct bch_opts bch2_opts_empty(void) { return (struct bch_opts) { 0 }; } void bch2_opts_apply(struct bch_opts *, struct bch_opts); enum bch_opt_id { #define x(_name, ...) Opt_##_name, BCH_OPTS() #undef x bch2_opts_nr }; struct bch_fs; struct printbuf; struct bch_option { struct attribute attr; u64 (*get_sb)(const struct bch_sb *); void (*set_sb)(struct bch_sb *, u64); enum opt_type type; enum opt_flags flags; u64 min, max; const char * const *choices; struct bch_opt_fn fn; const char *hint; const char *help; }; extern const struct bch_option bch2_opt_table[]; bool bch2_opt_defined_by_id(const struct bch_opts *, enum bch_opt_id); u64 bch2_opt_get_by_id(const struct bch_opts *, enum bch_opt_id); void bch2_opt_set_by_id(struct bch_opts *, enum bch_opt_id, u64); u64 bch2_opt_from_sb(struct bch_sb *, enum bch_opt_id); int bch2_opts_from_sb(struct bch_opts *, struct bch_sb *); void __bch2_opt_set_sb(struct bch_sb *, const struct bch_option *, u64); void bch2_opt_set_sb(struct bch_fs *, const struct bch_option *, u64); int bch2_opt_lookup(const char *); int bch2_opt_validate(const struct bch_option *, u64, struct printbuf *); int bch2_opt_parse(struct bch_fs *, const struct bch_option *, const char *, u64 *, struct printbuf *); #define OPT_SHOW_FULL_LIST (1 << 0) #define OPT_SHOW_MOUNT_STYLE (1 << 1) void bch2_opt_to_text(struct printbuf *, struct bch_fs *, struct bch_sb *, const struct bch_option *, u64, unsigned); int bch2_opt_check_may_set(struct bch_fs *, int, u64); int bch2_opts_check_may_set(struct bch_fs *); int bch2_parse_one_mount_opt(struct bch_fs *, struct bch_opts *, struct printbuf *, const char *, const char *); int bch2_parse_mount_opts(struct bch_fs *, struct bch_opts *, struct printbuf *, char *); /* inode opts: */ struct bch_io_opts { #define x(_name, _bits) u##_bits _name; BCH_INODE_OPTS() #undef x }; static inline unsigned background_compression(struct bch_io_opts opts) { return opts.background_compression ?: opts.compression; } struct bch_io_opts bch2_opts_to_inode_opts(struct bch_opts); bool bch2_opt_is_inode_opt(enum bch_opt_id); #endif /* _BCACHEFS_OPTS_H */ |
| 32 32 32 32 579 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API for algorithms (i.e., low-level API). * * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/algapi.h> #include <crypto/internal/simd.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/fips.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/module.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/workqueue.h> #include "internal.h" static LIST_HEAD(crypto_template_list); #ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS DEFINE_PER_CPU(bool, crypto_simd_disabled_for_test); EXPORT_PER_CPU_SYMBOL_GPL(crypto_simd_disabled_for_test); #endif static inline void crypto_check_module_sig(struct module *mod) { if (fips_enabled && mod && !module_sig_ok(mod)) panic("Module %s signature verification failed in FIPS mode\n", module_name(mod)); } static int crypto_check_alg(struct crypto_alg *alg) { crypto_check_module_sig(alg->cra_module); if (!alg->cra_name[0] || !alg->cra_driver_name[0]) return -EINVAL; if (alg->cra_alignmask & (alg->cra_alignmask + 1)) return -EINVAL; /* General maximums for all algs. */ if (alg->cra_alignmask > MAX_ALGAPI_ALIGNMASK) return -EINVAL; if (alg->cra_blocksize > MAX_ALGAPI_BLOCKSIZE) return -EINVAL; /* Lower maximums for specific alg types. */ if (!alg->cra_type && (alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_CIPHER) { if (alg->cra_alignmask > MAX_CIPHER_ALIGNMASK) return -EINVAL; if (alg->cra_blocksize > MAX_CIPHER_BLOCKSIZE) return -EINVAL; } if (alg->cra_priority < 0) return -EINVAL; refcount_set(&alg->cra_refcnt, 1); return 0; } static void crypto_free_instance(struct crypto_instance *inst) { inst->alg.cra_type->free(inst); } static void crypto_destroy_instance_workfn(struct work_struct *w) { struct crypto_instance *inst = container_of(w, struct crypto_instance, free_work); struct crypto_template *tmpl = inst->tmpl; crypto_free_instance(inst); crypto_tmpl_put(tmpl); } static void crypto_destroy_instance(struct crypto_alg *alg) { struct crypto_instance *inst = container_of(alg, struct crypto_instance, alg); INIT_WORK(&inst->free_work, crypto_destroy_instance_workfn); schedule_work(&inst->free_work); } /* * This function adds a spawn to the list secondary_spawns which * will be used at the end of crypto_remove_spawns to unregister * instances, unless the spawn happens to be one that is depended * on by the new algorithm (nalg in crypto_remove_spawns). * * This function is also responsible for resurrecting any algorithms * in the dependency chain of nalg by unsetting n->dead. */ static struct list_head *crypto_more_spawns(struct crypto_alg *alg, struct list_head *stack, struct list_head *top, struct list_head *secondary_spawns) { struct crypto_spawn *spawn, *n; spawn = list_first_entry_or_null(stack, struct crypto_spawn, list); if (!spawn) return NULL; n = list_prev_entry(spawn, list); list_move(&spawn->list, secondary_spawns); if (list_is_last(&n->list, stack)) return top; n = list_next_entry(n, list); if (!spawn->dead) n->dead = false; return &n->inst->alg.cra_users; } static void crypto_remove_instance(struct crypto_instance *inst, struct list_head *list) { struct crypto_template *tmpl = inst->tmpl; if (crypto_is_dead(&inst->alg)) return; inst->alg.cra_flags |= CRYPTO_ALG_DEAD; if (!tmpl || !crypto_tmpl_get(tmpl)) return; list_move(&inst->alg.cra_list, list); hlist_del(&inst->list); inst->alg.cra_destroy = crypto_destroy_instance; BUG_ON(!list_empty(&inst->alg.cra_users)); } /* * Given an algorithm alg, remove all algorithms that depend on it * through spawns. If nalg is not null, then exempt any algorithms * that is depended on by nalg. This is useful when nalg itself * depends on alg. */ void crypto_remove_spawns(struct crypto_alg *alg, struct list_head *list, struct crypto_alg *nalg) { u32 new_type = (nalg ?: alg)->cra_flags; struct crypto_spawn *spawn, *n; LIST_HEAD(secondary_spawns); struct list_head *spawns; LIST_HEAD(stack); LIST_HEAD(top); spawns = &alg->cra_users; list_for_each_entry_safe(spawn, n, spawns, list) { if ((spawn->alg->cra_flags ^ new_type) & spawn->mask) continue; list_move(&spawn->list, &top); } /* * Perform a depth-first walk starting from alg through * the cra_users tree. The list stack records the path * from alg to the current spawn. */ spawns = ⊤ do { while (!list_empty(spawns)) { struct crypto_instance *inst; spawn = list_first_entry(spawns, struct crypto_spawn, list); inst = spawn->inst; list_move(&spawn->list, &stack); spawn->dead = !spawn->registered || &inst->alg != nalg; if (!spawn->registered) break; BUG_ON(&inst->alg == alg); if (&inst->alg == nalg) break; spawns = &inst->alg.cra_users; /* * Even if spawn->registered is true, the * instance itself may still be unregistered. * This is because it may have failed during * registration. Therefore we still need to * make the following test. * * We may encounter an unregistered instance here, since * an instance's spawns are set up prior to the instance * being registered. An unregistered instance will have * NULL ->cra_users.next, since ->cra_users isn't * properly initialized until registration. But an * unregistered instance cannot have any users, so treat * it the same as ->cra_users being empty. */ if (spawns->next == NULL) break; } } while ((spawns = crypto_more_spawns(alg, &stack, &top, &secondary_spawns))); /* * Remove all instances that are marked as dead. Also * complete the resurrection of the others by moving them * back to the cra_users list. */ list_for_each_entry_safe(spawn, n, &secondary_spawns, list) { if (!spawn->dead) list_move(&spawn->list, &spawn->alg->cra_users); else if (spawn->registered) crypto_remove_instance(spawn->inst, list); } } EXPORT_SYMBOL_GPL(crypto_remove_spawns); static void crypto_alg_finish_registration(struct crypto_alg *alg, bool fulfill_requests, struct list_head *algs_to_put) { struct crypto_alg *q; list_for_each_entry(q, &crypto_alg_list, cra_list) { if (q == alg) continue; if (crypto_is_moribund(q)) continue; if (crypto_is_larval(q)) { struct crypto_larval *larval = (void *)q; /* * Check to see if either our generic name or * specific name can satisfy the name requested * by the larval entry q. */ if (strcmp(alg->cra_name, q->cra_name) && strcmp(alg->cra_driver_name, q->cra_name)) continue; if (larval->adult) continue; if ((q->cra_flags ^ alg->cra_flags) & larval->mask) continue; if (fulfill_requests && crypto_mod_get(alg)) larval->adult = alg; else larval->adult = ERR_PTR(-EAGAIN); continue; } if (strcmp(alg->cra_name, q->cra_name)) continue; if (strcmp(alg->cra_driver_name, q->cra_driver_name) && q->cra_priority > alg->cra_priority) continue; crypto_remove_spawns(q, algs_to_put, alg); } crypto_notify(CRYPTO_MSG_ALG_LOADED, alg); } static struct crypto_larval *crypto_alloc_test_larval(struct crypto_alg *alg) { struct crypto_larval *larval; if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER) || IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) || (alg->cra_flags & CRYPTO_ALG_INTERNAL)) return NULL; /* No self-test needed */ larval = crypto_larval_alloc(alg->cra_name, alg->cra_flags | CRYPTO_ALG_TESTED, 0); if (IS_ERR(larval)) return larval; larval->adult = crypto_mod_get(alg); if (!larval->adult) { kfree(larval); return ERR_PTR(-ENOENT); } refcount_set(&larval->alg.cra_refcnt, 1); memcpy(larval->alg.cra_driver_name, alg->cra_driver_name, CRYPTO_MAX_ALG_NAME); larval->alg.cra_priority = alg->cra_priority; return larval; } static struct crypto_larval * __crypto_register_alg(struct crypto_alg *alg, struct list_head *algs_to_put) { struct crypto_alg *q; struct crypto_larval *larval; int ret = -EAGAIN; if (crypto_is_dead(alg)) goto err; INIT_LIST_HEAD(&alg->cra_users); ret = -EEXIST; list_for_each_entry(q, &crypto_alg_list, cra_list) { if (q == alg) goto err; if (crypto_is_moribund(q)) continue; if (crypto_is_larval(q)) { if (!strcmp(alg->cra_driver_name, q->cra_driver_name)) goto err; continue; } if (!strcmp(q->cra_driver_name, alg->cra_name) || !strcmp(q->cra_driver_name, alg->cra_driver_name) || !strcmp(q->cra_name, alg->cra_driver_name)) goto err; } larval = crypto_alloc_test_larval(alg); if (IS_ERR(larval)) goto out; list_add(&alg->cra_list, &crypto_alg_list); if (larval) { /* No cheating! */ alg->cra_flags &= ~CRYPTO_ALG_TESTED; list_add(&larval->alg.cra_list, &crypto_alg_list); } else { alg->cra_flags |= CRYPTO_ALG_TESTED; crypto_alg_finish_registration(alg, true, algs_to_put); } out: return larval; err: larval = ERR_PTR(ret); goto out; } void crypto_alg_tested(const char *name, int err) { struct crypto_larval *test; struct crypto_alg *alg; struct crypto_alg *q; LIST_HEAD(list); bool best; down_write(&crypto_alg_sem); list_for_each_entry(q, &crypto_alg_list, cra_list) { if (crypto_is_moribund(q) || !crypto_is_larval(q)) continue; test = (struct crypto_larval *)q; if (!strcmp(q->cra_driver_name, name)) goto found; } pr_err("alg: Unexpected test result for %s: %d\n", name, err); goto unlock; found: q->cra_flags |= CRYPTO_ALG_DEAD; alg = test->adult; if (list_empty(&alg->cra_list)) goto complete; if (err == -ECANCELED) alg->cra_flags |= CRYPTO_ALG_FIPS_INTERNAL; else if (err) goto complete; else alg->cra_flags &= ~CRYPTO_ALG_FIPS_INTERNAL; alg->cra_flags |= CRYPTO_ALG_TESTED; /* * If a higher-priority implementation of the same algorithm is * currently being tested, then don't fulfill request larvals. */ best = true; list_for_each_entry(q, &crypto_alg_list, cra_list) { if (crypto_is_moribund(q) || !crypto_is_larval(q)) continue; if (strcmp(alg->cra_name, q->cra_name)) continue; if (q->cra_priority > alg->cra_priority) { best = false; break; } } crypto_alg_finish_registration(alg, best, &list); complete: complete_all(&test->completion); unlock: up_write(&crypto_alg_sem); crypto_remove_final(&list); } EXPORT_SYMBOL_GPL(crypto_alg_tested); void crypto_remove_final(struct list_head *list) { struct crypto_alg *alg; struct crypto_alg *n; list_for_each_entry_safe(alg, n, list, cra_list) { list_del_init(&alg->cra_list); crypto_alg_put(alg); } } EXPORT_SYMBOL_GPL(crypto_remove_final); int crypto_register_alg(struct crypto_alg *alg) { struct crypto_larval *larval; LIST_HEAD(algs_to_put); bool test_started = false; int err; alg->cra_flags &= ~CRYPTO_ALG_DEAD; err = crypto_check_alg(alg); if (err) return err; down_write(&crypto_alg_sem); larval = __crypto_register_alg(alg, &algs_to_put); if (!IS_ERR_OR_NULL(larval)) { test_started = crypto_boot_test_finished(); larval->test_started = test_started; } up_write(&crypto_alg_sem); if (IS_ERR(larval)) return PTR_ERR(larval); if (test_started) crypto_wait_for_test(larval); crypto_remove_final(&algs_to_put); return 0; } EXPORT_SYMBOL_GPL(crypto_register_alg); static int crypto_remove_alg(struct crypto_alg *alg, struct list_head *list) { if (unlikely(list_empty(&alg->cra_list))) return -ENOENT; alg->cra_flags |= CRYPTO_ALG_DEAD; list_del_init(&alg->cra_list); crypto_remove_spawns(alg, list, NULL); return 0; } void crypto_unregister_alg(struct crypto_alg *alg) { int ret; LIST_HEAD(list); down_write(&crypto_alg_sem); ret = crypto_remove_alg(alg, &list); up_write(&crypto_alg_sem); if (WARN(ret, "Algorithm %s is not registered", alg->cra_driver_name)) return; if (WARN_ON(refcount_read(&alg->cra_refcnt) != 1)) return; if (alg->cra_destroy) alg->cra_destroy(alg); crypto_remove_final(&list); } EXPORT_SYMBOL_GPL(crypto_unregister_alg); int crypto_register_algs(struct crypto_alg *algs, int count) { int i, ret; for (i = 0; i < count; i++) { ret = crypto_register_alg(&algs[i]); if (ret) goto err; } return 0; err: for (--i; i >= 0; --i) crypto_unregister_alg(&algs[i]); return ret; } EXPORT_SYMBOL_GPL(crypto_register_algs); void crypto_unregister_algs(struct crypto_alg *algs, int count) { int i; for (i = 0; i < count; i++) crypto_unregister_alg(&algs[i]); } EXPORT_SYMBOL_GPL(crypto_unregister_algs); int crypto_register_template(struct crypto_template *tmpl) { struct crypto_template *q; int err = -EEXIST; down_write(&crypto_alg_sem); crypto_check_module_sig(tmpl->module); list_for_each_entry(q, &crypto_template_list, list) { if (q == tmpl) goto out; } list_add(&tmpl->list, &crypto_template_list); err = 0; out: up_write(&crypto_alg_sem); return err; } EXPORT_SYMBOL_GPL(crypto_register_template); int crypto_register_templates(struct crypto_template *tmpls, int count) { int i, err; for (i = 0; i < count; i++) { err = crypto_register_template(&tmpls[i]); if (err) goto out; } return 0; out: for (--i; i >= 0; --i) crypto_unregister_template(&tmpls[i]); return err; } EXPORT_SYMBOL_GPL(crypto_register_templates); void crypto_unregister_template(struct crypto_template *tmpl) { struct crypto_instance *inst; struct hlist_node *n; struct hlist_head *list; LIST_HEAD(users); down_write(&crypto_alg_sem); BUG_ON(list_empty(&tmpl->list)); list_del_init(&tmpl->list); list = &tmpl->instances; hlist_for_each_entry(inst, list, list) { int err = crypto_remove_alg(&inst->alg, &users); BUG_ON(err); } up_write(&crypto_alg_sem); hlist_for_each_entry_safe(inst, n, list, list) { BUG_ON(refcount_read(&inst->alg.cra_refcnt) != 1); crypto_free_instance(inst); } crypto_remove_final(&users); } EXPORT_SYMBOL_GPL(crypto_unregister_template); void crypto_unregister_templates(struct crypto_template *tmpls, int count) { int i; for (i = count - 1; i >= 0; --i) crypto_unregister_template(&tmpls[i]); } EXPORT_SYMBOL_GPL(crypto_unregister_templates); static struct crypto_template *__crypto_lookup_template(const char *name) { struct crypto_template *q, *tmpl = NULL; down_read(&crypto_alg_sem); list_for_each_entry(q, &crypto_template_list, list) { if (strcmp(q->name, name)) continue; if (unlikely(!crypto_tmpl_get(q))) continue; tmpl = q; break; } up_read(&crypto_alg_sem); return tmpl; } struct crypto_template *crypto_lookup_template(const char *name) { return try_then_request_module(__crypto_lookup_template(name), "crypto-%s", name); } EXPORT_SYMBOL_GPL(crypto_lookup_template); int crypto_register_instance(struct crypto_template *tmpl, struct crypto_instance *inst) { struct crypto_larval *larval; struct crypto_spawn *spawn; u32 fips_internal = 0; LIST_HEAD(algs_to_put); int err; err = crypto_check_alg(&inst->alg); if (err) return err; inst->alg.cra_module = tmpl->module; inst->alg.cra_flags |= CRYPTO_ALG_INSTANCE; down_write(&crypto_alg_sem); larval = ERR_PTR(-EAGAIN); for (spawn = inst->spawns; spawn;) { struct crypto_spawn *next; if (spawn->dead) goto unlock; next = spawn->next; spawn->inst = inst; spawn->registered = true; fips_internal |= spawn->alg->cra_flags; crypto_mod_put(spawn->alg); spawn = next; } inst->alg.cra_flags |= (fips_internal & CRYPTO_ALG_FIPS_INTERNAL); larval = __crypto_register_alg(&inst->alg, &algs_to_put); if (IS_ERR(larval)) goto unlock; else if (larval) larval->test_started = true; hlist_add_head(&inst->list, &tmpl->instances); inst->tmpl = tmpl; unlock: up_write(&crypto_alg_sem); if (IS_ERR(larval)) return PTR_ERR(larval); if (larval) crypto_wait_for_test(larval); crypto_remove_final(&algs_to_put); return 0; } EXPORT_SYMBOL_GPL(crypto_register_instance); void crypto_unregister_instance(struct crypto_instance *inst) { LIST_HEAD(list); down_write(&crypto_alg_sem); crypto_remove_spawns(&inst->alg, &list, NULL); crypto_remove_instance(inst, &list); up_write(&crypto_alg_sem); crypto_remove_final(&list); } EXPORT_SYMBOL_GPL(crypto_unregister_instance); int crypto_grab_spawn(struct crypto_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { struct crypto_alg *alg; int err = -EAGAIN; if (WARN_ON_ONCE(inst == NULL)) return -EINVAL; /* Allow the result of crypto_attr_alg_name() to be passed directly */ if (IS_ERR(name)) return PTR_ERR(name); alg = crypto_find_alg(name, spawn->frontend, type | CRYPTO_ALG_FIPS_INTERNAL, mask); if (IS_ERR(alg)) return PTR_ERR(alg); down_write(&crypto_alg_sem); if (!crypto_is_moribund(alg)) { list_add(&spawn->list, &alg->cra_users); spawn->alg = alg; spawn->mask = mask; spawn->next = inst->spawns; inst->spawns = spawn; inst->alg.cra_flags |= (alg->cra_flags & CRYPTO_ALG_INHERITED_FLAGS); err = 0; } up_write(&crypto_alg_sem); if (err) crypto_mod_put(alg); return err; } EXPORT_SYMBOL_GPL(crypto_grab_spawn); void crypto_drop_spawn(struct crypto_spawn *spawn) { if (!spawn->alg) /* not yet initialized? */ return; down_write(&crypto_alg_sem); if (!spawn->dead) list_del(&spawn->list); up_write(&crypto_alg_sem); if (!spawn->registered) crypto_mod_put(spawn->alg); } EXPORT_SYMBOL_GPL(crypto_drop_spawn); static struct crypto_alg *crypto_spawn_alg(struct crypto_spawn *spawn) { struct crypto_alg *alg = ERR_PTR(-EAGAIN); struct crypto_alg *target; bool shoot = false; down_read(&crypto_alg_sem); if (!spawn->dead) { alg = spawn->alg; if (!crypto_mod_get(alg)) { target = crypto_alg_get(alg); shoot = true; alg = ERR_PTR(-EAGAIN); } } up_read(&crypto_alg_sem); if (shoot) { crypto_shoot_alg(target); crypto_alg_put(target); } return alg; } struct crypto_tfm *crypto_spawn_tfm(struct crypto_spawn *spawn, u32 type, u32 mask) { struct crypto_alg *alg; struct crypto_tfm *tfm; alg = crypto_spawn_alg(spawn); if (IS_ERR(alg)) return ERR_CAST(alg); tfm = ERR_PTR(-EINVAL); if (unlikely((alg->cra_flags ^ type) & mask)) goto out_put_alg; tfm = __crypto_alloc_tfm(alg, type, mask); if (IS_ERR(tfm)) goto out_put_alg; return tfm; out_put_alg: crypto_mod_put(alg); return tfm; } EXPORT_SYMBOL_GPL(crypto_spawn_tfm); void *crypto_spawn_tfm2(struct crypto_spawn *spawn) { struct crypto_alg *alg; struct crypto_tfm *tfm; alg = crypto_spawn_alg(spawn); if (IS_ERR(alg)) return ERR_CAST(alg); tfm = crypto_create_tfm(alg, spawn->frontend); if (IS_ERR(tfm)) goto out_put_alg; return tfm; out_put_alg: crypto_mod_put(alg); return tfm; } EXPORT_SYMBOL_GPL(crypto_spawn_tfm2); int crypto_register_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&crypto_chain, nb); } EXPORT_SYMBOL_GPL(crypto_register_notifier); int crypto_unregister_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&crypto_chain, nb); } EXPORT_SYMBOL_GPL(crypto_unregister_notifier); struct crypto_attr_type *crypto_get_attr_type(struct rtattr **tb) { struct rtattr *rta = tb[0]; struct crypto_attr_type *algt; if (!rta) return ERR_PTR(-ENOENT); if (RTA_PAYLOAD(rta) < sizeof(*algt)) return ERR_PTR(-EINVAL); if (rta->rta_type != CRYPTOA_TYPE) return ERR_PTR(-EINVAL); algt = RTA_DATA(rta); return algt; } EXPORT_SYMBOL_GPL(crypto_get_attr_type); /** * crypto_check_attr_type() - check algorithm type and compute inherited mask * @tb: the template parameters * @type: the algorithm type the template would be instantiated as * @mask_ret: (output) the mask that should be passed to crypto_grab_*() * to restrict the flags of any inner algorithms * * Validate that the algorithm type the user requested is compatible with the * one the template would actually be instantiated as. E.g., if the user is * doing crypto_alloc_shash("cbc(aes)", ...), this would return an error because * the "cbc" template creates an "skcipher" algorithm, not an "shash" algorithm. * * Also compute the mask to use to restrict the flags of any inner algorithms. * * Return: 0 on success; -errno on failure */ int crypto_check_attr_type(struct rtattr **tb, u32 type, u32 *mask_ret) { struct crypto_attr_type *algt; algt = crypto_get_attr_type(tb); if (IS_ERR(algt)) return PTR_ERR(algt); if ((algt->type ^ type) & algt->mask) return -EINVAL; *mask_ret = crypto_algt_inherited_mask(algt); return 0; } EXPORT_SYMBOL_GPL(crypto_check_attr_type); const char *crypto_attr_alg_name(struct rtattr *rta) { struct crypto_attr_alg *alga; if (!rta) return ERR_PTR(-ENOENT); if (RTA_PAYLOAD(rta) < sizeof(*alga)) return ERR_PTR(-EINVAL); if (rta->rta_type != CRYPTOA_ALG) return ERR_PTR(-EINVAL); alga = RTA_DATA(rta); alga->name[CRYPTO_MAX_ALG_NAME - 1] = 0; return alga->name; } EXPORT_SYMBOL_GPL(crypto_attr_alg_name); int crypto_inst_setname(struct crypto_instance *inst, const char *name, struct crypto_alg *alg) { if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", name, alg->cra_name) >= CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", name, alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME) return -ENAMETOOLONG; return 0; } EXPORT_SYMBOL_GPL(crypto_inst_setname); void crypto_init_queue(struct crypto_queue *queue, unsigned int max_qlen) { INIT_LIST_HEAD(&queue->list); queue->backlog = &queue->list; queue->qlen = 0; queue->max_qlen = max_qlen; } EXPORT_SYMBOL_GPL(crypto_init_queue); int crypto_enqueue_request(struct crypto_queue *queue, struct crypto_async_request *request) { int err = -EINPROGRESS; if (unlikely(queue->qlen >= queue->max_qlen)) { if (!(request->flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) { err = -ENOSPC; goto out; } err = -EBUSY; if (queue->backlog == &queue->list) queue->backlog = &request->list; } queue->qlen++; list_add_tail(&request->list, &queue->list); out: return err; } EXPORT_SYMBOL_GPL(crypto_enqueue_request); void crypto_enqueue_request_head(struct crypto_queue *queue, struct crypto_async_request *request) { if (unlikely(queue->qlen >= queue->max_qlen)) queue->backlog = queue->backlog->prev; queue->qlen++; list_add(&request->list, &queue->list); } EXPORT_SYMBOL_GPL(crypto_enqueue_request_head); struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue) { struct list_head *request; if (unlikely(!queue->qlen)) return NULL; queue->qlen--; if (queue->backlog != &queue->list) queue->backlog = queue->backlog->next; request = queue->list.next; list_del(request); return list_entry(request, struct crypto_async_request, list); } EXPORT_SYMBOL_GPL(crypto_dequeue_request); static inline void crypto_inc_byte(u8 *a, unsigned int size) { u8 *b = (a + size); u8 c; for (; size; size--) { c = *--b + 1; *b = c; if (c) break; } } void crypto_inc(u8 *a, unsigned int size) { __be32 *b = (__be32 *)(a + size); u32 c; if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || IS_ALIGNED((unsigned long)b, __alignof__(*b))) for (; size >= 4; size -= 4) { c = be32_to_cpu(*--b) + 1; *b = cpu_to_be32(c); if (likely(c)) return; } crypto_inc_byte(a, size); } EXPORT_SYMBOL_GPL(crypto_inc); unsigned int crypto_alg_extsize(struct crypto_alg *alg) { return alg->cra_ctxsize + (alg->cra_alignmask & ~(crypto_tfm_ctx_alignment() - 1)); } EXPORT_SYMBOL_GPL(crypto_alg_extsize); int crypto_type_has_alg(const char *name, const struct crypto_type *frontend, u32 type, u32 mask) { int ret = 0; struct crypto_alg *alg = crypto_find_alg(name, frontend, type, mask); if (!IS_ERR(alg)) { crypto_mod_put(alg); ret = 1; } return ret; } EXPORT_SYMBOL_GPL(crypto_type_has_alg); static void __init crypto_start_tests(void) { if (!IS_BUILTIN(CONFIG_CRYPTO_ALGAPI)) return; if (IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS)) return; for (;;) { struct crypto_larval *larval = NULL; struct crypto_alg *q; down_write(&crypto_alg_sem); list_for_each_entry(q, &crypto_alg_list, cra_list) { struct crypto_larval *l; if (!crypto_is_larval(q)) continue; l = (void *)q; if (!crypto_is_test_larval(l)) continue; if (l->test_started) continue; l->test_started = true; larval = l; break; } up_write(&crypto_alg_sem); if (!larval) break; crypto_wait_for_test(larval); } set_crypto_boot_test_finished(); } static int __init crypto_algapi_init(void) { crypto_init_proc(); crypto_start_tests(); return 0; } static void __exit crypto_algapi_exit(void) { crypto_exit_proc(); } /* * We run this at late_initcall so that all the built-in algorithms * have had a chance to register themselves first. */ late_initcall(crypto_algapi_init); module_exit(crypto_algapi_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Cryptographic algorithms API"); MODULE_SOFTDEP("pre: cryptomgr"); |
| 4 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | // SPDX-License-Identifier: GPL-2.0-only /* * * Authors: * (C) 2015 Pengutronix, Alexander Aring <aar@pengutronix.de> */ #include <linux/if_arp.h> #include <linux/module.h> #include <net/6lowpan.h> #include <net/addrconf.h> #include "6lowpan_i.h" int lowpan_register_netdevice(struct net_device *dev, enum lowpan_lltypes lltype) { int i, ret; switch (lltype) { case LOWPAN_LLTYPE_IEEE802154: dev->addr_len = EUI64_ADDR_LEN; break; case LOWPAN_LLTYPE_BTLE: dev->addr_len = ETH_ALEN; break; } dev->type = ARPHRD_6LOWPAN; dev->mtu = IPV6_MIN_MTU; lowpan_dev(dev)->lltype = lltype; spin_lock_init(&lowpan_dev(dev)->ctx.lock); for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) lowpan_dev(dev)->ctx.table[i].id = i; dev->ndisc_ops = &lowpan_ndisc_ops; ret = register_netdevice(dev); if (ret < 0) return ret; lowpan_dev_debugfs_init(dev); return ret; } EXPORT_SYMBOL(lowpan_register_netdevice); int lowpan_register_netdev(struct net_device *dev, enum lowpan_lltypes lltype) { int ret; rtnl_lock(); ret = lowpan_register_netdevice(dev, lltype); rtnl_unlock(); return ret; } EXPORT_SYMBOL(lowpan_register_netdev); void lowpan_unregister_netdevice(struct net_device *dev) { unregister_netdevice(dev); lowpan_dev_debugfs_exit(dev); } EXPORT_SYMBOL(lowpan_unregister_netdevice); void lowpan_unregister_netdev(struct net_device *dev) { rtnl_lock(); lowpan_unregister_netdevice(dev); rtnl_unlock(); } EXPORT_SYMBOL(lowpan_unregister_netdev); int addrconf_ifid_802154_6lowpan(u8 *eui, struct net_device *dev) { struct wpan_dev *wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr; /* Set short_addr autoconfiguration if short_addr is present only */ if (!lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr)) return -1; /* For either address format, all zero addresses MUST NOT be used */ if (wpan_dev->pan_id == cpu_to_le16(0x0000) && wpan_dev->short_addr == cpu_to_le16(0x0000)) return -1; /* Alternatively, if no PAN ID is known, 16 zero bits may be used */ if (wpan_dev->pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST)) memset(eui, 0, 2); else ieee802154_le16_to_be16(eui, &wpan_dev->pan_id); /* The "Universal/Local" (U/L) bit shall be set to zero */ eui[0] &= ~2; eui[2] = 0; eui[3] = 0xFF; eui[4] = 0xFE; eui[5] = 0; ieee802154_le16_to_be16(&eui[6], &wpan_dev->short_addr); return 0; } static int lowpan_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev; struct in6_addr addr; int i; if (dev->type != ARPHRD_6LOWPAN) return NOTIFY_DONE; idev = __in6_dev_get(dev); if (!idev) return NOTIFY_DONE; switch (event) { case NETDEV_UP: case NETDEV_CHANGE: /* (802.15.4 6LoWPAN short address slaac handling */ if (lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154) && addrconf_ifid_802154_6lowpan(addr.s6_addr + 8, dev) == 0) { __ipv6_addr_set_half(&addr.s6_addr32[0], htonl(0xFE800000), 0); addrconf_add_linklocal(idev, &addr, 0); } break; case NETDEV_DOWN: for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++) clear_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, &lowpan_dev(dev)->ctx.table[i].flags); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block lowpan_notifier = { .notifier_call = lowpan_event, }; static int __init lowpan_module_init(void) { int ret; lowpan_debugfs_init(); ret = register_netdevice_notifier(&lowpan_notifier); if (ret < 0) { lowpan_debugfs_exit(); return ret; } request_module_nowait("nhc_dest"); request_module_nowait("nhc_fragment"); request_module_nowait("nhc_hop"); request_module_nowait("nhc_ipv6"); request_module_nowait("nhc_mobility"); request_module_nowait("nhc_routing"); request_module_nowait("nhc_udp"); return 0; } static void __exit lowpan_module_exit(void) { lowpan_debugfs_exit(); unregister_netdevice_notifier(&lowpan_notifier); } module_init(lowpan_module_init); module_exit(lowpan_module_exit); MODULE_DESCRIPTION("IPv6 over Low-Power Wireless Personal Area Network core module"); MODULE_LICENSE("GPL"); |
| 3 43 42 227 209 1 66 197 83 256 357 72 206 47 217 194 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FAT_H #define _FAT_H #include <linux/buffer_head.h> #include <linux/nls.h> #include <linux/hash.h> #include <linux/ratelimit.h> #include <linux/msdos_fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> /* * vfat shortname flags */ #define VFAT_SFN_DISPLAY_LOWER 0x0001 /* convert to lowercase for display */ #define VFAT_SFN_DISPLAY_WIN95 0x0002 /* emulate win95 rule for display */ #define VFAT_SFN_DISPLAY_WINNT 0x0004 /* emulate winnt rule for display */ #define VFAT_SFN_CREATE_WIN95 0x0100 /* emulate win95 rule for create */ #define VFAT_SFN_CREATE_WINNT 0x0200 /* emulate winnt rule for create */ #define FAT_ERRORS_CONT 1 /* ignore error and continue */ #define FAT_ERRORS_PANIC 2 /* panic on error */ #define FAT_ERRORS_RO 3 /* remount r/o on error */ #define FAT_NFS_STALE_RW 1 /* NFS RW support, can cause ESTALE */ #define FAT_NFS_NOSTALE_RO 2 /* NFS RO support, no ESTALE issue */ struct fat_mount_options { kuid_t fs_uid; kgid_t fs_gid; unsigned short fs_fmask; unsigned short fs_dmask; unsigned short codepage; /* Codepage for shortname conversions */ int time_offset; /* Offset of timestamps from UTC (in minutes) */ char *iocharset; /* Charset used for filename input/display */ unsigned short shortname; /* flags for shortname display/create rule */ unsigned char name_check; /* r = relaxed, n = normal, s = strict */ unsigned char errors; /* On error: continue, panic, remount-ro */ unsigned char nfs; /* NFS support: nostale_ro, stale_rw */ unsigned short allow_utime;/* permission for setting the [am]time */ unsigned quiet:1, /* set = fake successful chmods and chowns */ showexec:1, /* set = only set x bit for com/exe/bat */ sys_immutable:1, /* set = system files are immutable */ dotsOK:1, /* set = hidden and system files are named '.filename' */ isvfat:1, /* 0=no vfat long filename support, 1=vfat support */ utf8:1, /* Use of UTF-8 character set (Default) */ unicode_xlate:1, /* create escape sequences for unhandled Unicode */ numtail:1, /* Does first alias have a numeric '~1' type tail? */ flush:1, /* write things quickly */ nocase:1, /* Does this need case conversion? 0=need case conversion*/ usefree:1, /* Use free_clusters for FAT32 */ tz_set:1, /* Filesystem timestamps' offset set */ rodir:1, /* allow ATTR_RO for directory */ discard:1, /* Issue discard requests on deletions */ dos1xfloppy:1, /* Assume default BPB for DOS 1.x floppies */ debug:1; /* Not currently used */ }; #define FAT_HASH_BITS 8 #define FAT_HASH_SIZE (1UL << FAT_HASH_BITS) /* * MS-DOS file system in-core superblock data */ struct msdos_sb_info { unsigned short sec_per_clus; /* sectors/cluster */ unsigned short cluster_bits; /* log2(cluster_size) */ unsigned int cluster_size; /* cluster size */ unsigned char fats, fat_bits; /* number of FATs, FAT bits (12,16 or 32) */ unsigned short fat_start; unsigned long fat_length; /* FAT start & length (sec.) */ unsigned long dir_start; unsigned short dir_entries; /* root dir start & entries */ unsigned long data_start; /* first data sector */ unsigned long max_cluster; /* maximum cluster number */ unsigned long root_cluster; /* first cluster of the root directory */ unsigned long fsinfo_sector; /* sector number of FAT32 fsinfo */ struct mutex fat_lock; struct mutex nfs_build_inode_lock; struct mutex s_lock; unsigned int prev_free; /* previously allocated cluster number */ unsigned int free_clusters; /* -1 if undefined */ unsigned int free_clus_valid; /* is free_clusters valid? */ struct fat_mount_options options; struct nls_table *nls_disk; /* Codepage used on disk */ struct nls_table *nls_io; /* Charset used for input and display */ const void *dir_ops; /* Opaque; default directory operations */ int dir_per_block; /* dir entries per block */ int dir_per_block_bits; /* log2(dir_per_block) */ unsigned int vol_id; /*volume ID*/ int fatent_shift; const struct fatent_operations *fatent_ops; struct inode *fat_inode; struct inode *fsinfo_inode; struct ratelimit_state ratelimit; spinlock_t inode_hash_lock; struct hlist_head inode_hashtable[FAT_HASH_SIZE]; spinlock_t dir_hash_lock; struct hlist_head dir_hashtable[FAT_HASH_SIZE]; unsigned int dirty; /* fs state before mount */ struct rcu_head rcu; }; #define FAT_CACHE_VALID 0 /* special case for valid cache */ /* * MS-DOS file system inode data in memory */ struct msdos_inode_info { spinlock_t cache_lru_lock; struct list_head cache_lru; int nr_caches; /* for avoiding the race between fat_free() and fat_get_cluster() */ unsigned int cache_valid_id; /* NOTE: mmu_private is 64bits, so must hold ->i_mutex to access */ loff_t mmu_private; /* physically allocated size */ int i_start; /* first cluster or 0 */ int i_logstart; /* logical first cluster */ int i_attrs; /* unused attribute bits */ loff_t i_pos; /* on-disk position of directory entry or 0 */ struct hlist_node i_fat_hash; /* hash by i_location */ struct hlist_node i_dir_hash; /* hash by i_logstart */ struct rw_semaphore truncate_lock; /* protect bmap against truncate */ struct timespec64 i_crtime; /* File creation (birth) time */ struct inode vfs_inode; }; struct fat_slot_info { loff_t i_pos; /* on-disk position of directory entry */ loff_t slot_off; /* offset for slot or de start */ int nr_slots; /* number of slots + 1(de) in filename */ struct msdos_dir_entry *de; struct buffer_head *bh; }; static inline struct msdos_sb_info *MSDOS_SB(struct super_block *sb) { return sb->s_fs_info; } /* * Functions that determine the variant of the FAT file system (i.e., * whether this is FAT12, FAT16 or FAT32. */ static inline bool is_fat12(const struct msdos_sb_info *sbi) { return sbi->fat_bits == 12; } static inline bool is_fat16(const struct msdos_sb_info *sbi) { return sbi->fat_bits == 16; } static inline bool is_fat32(const struct msdos_sb_info *sbi) { return sbi->fat_bits == 32; } /* Maximum number of clusters */ static inline u32 max_fat(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); return is_fat32(sbi) ? MAX_FAT32 : is_fat16(sbi) ? MAX_FAT16 : MAX_FAT12; } static inline struct msdos_inode_info *MSDOS_I(struct inode *inode) { return container_of(inode, struct msdos_inode_info, vfs_inode); } /* * If ->i_mode can't hold S_IWUGO (i.e. ATTR_RO), we use ->i_attrs to * save ATTR_RO instead of ->i_mode. * * If it's directory and !sbi->options.rodir, ATTR_RO isn't read-only * bit, it's just used as flag for app. */ static inline int fat_mode_can_hold_ro(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); umode_t mask; if (S_ISDIR(inode->i_mode)) { if (!sbi->options.rodir) return 0; mask = ~sbi->options.fs_dmask; } else mask = ~sbi->options.fs_fmask; if (!(mask & S_IWUGO)) return 0; return 1; } /* Convert attribute bits and a mask to the UNIX mode. */ static inline umode_t fat_make_mode(struct msdos_sb_info *sbi, u8 attrs, umode_t mode) { if (attrs & ATTR_RO && !((attrs & ATTR_DIR) && !sbi->options.rodir)) mode &= ~S_IWUGO; if (attrs & ATTR_DIR) return (mode & ~sbi->options.fs_dmask) | S_IFDIR; else return (mode & ~sbi->options.fs_fmask) | S_IFREG; } /* Return the FAT attribute byte for this inode */ static inline u8 fat_make_attrs(struct inode *inode) { u8 attrs = MSDOS_I(inode)->i_attrs; if (S_ISDIR(inode->i_mode)) attrs |= ATTR_DIR; if (fat_mode_can_hold_ro(inode) && !(inode->i_mode & S_IWUGO)) attrs |= ATTR_RO; return attrs; } static inline void fat_save_attrs(struct inode *inode, u8 attrs) { if (fat_mode_can_hold_ro(inode)) MSDOS_I(inode)->i_attrs = attrs & ATTR_UNUSED; else MSDOS_I(inode)->i_attrs = attrs & (ATTR_UNUSED | ATTR_RO); } static inline unsigned char fat_checksum(const __u8 *name) { unsigned char s = name[0]; s = (s<<7) + (s>>1) + name[1]; s = (s<<7) + (s>>1) + name[2]; s = (s<<7) + (s>>1) + name[3]; s = (s<<7) + (s>>1) + name[4]; s = (s<<7) + (s>>1) + name[5]; s = (s<<7) + (s>>1) + name[6]; s = (s<<7) + (s>>1) + name[7]; s = (s<<7) + (s>>1) + name[8]; s = (s<<7) + (s>>1) + name[9]; s = (s<<7) + (s>>1) + name[10]; return s; } static inline sector_t fat_clus_to_blknr(struct msdos_sb_info *sbi, int clus) { return ((sector_t)clus - FAT_START_ENT) * sbi->sec_per_clus + sbi->data_start; } static inline void fat_get_blknr_offset(struct msdos_sb_info *sbi, loff_t i_pos, sector_t *blknr, int *offset) { *blknr = i_pos >> sbi->dir_per_block_bits; *offset = i_pos & (sbi->dir_per_block - 1); } static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi, struct inode *inode) { loff_t i_pos; #if BITS_PER_LONG == 32 spin_lock(&sbi->inode_hash_lock); #endif i_pos = MSDOS_I(inode)->i_pos; #if BITS_PER_LONG == 32 spin_unlock(&sbi->inode_hash_lock); #endif return i_pos; } static inline void fat16_towchar(wchar_t *dst, const __u8 *src, size_t len) { #ifdef __BIG_ENDIAN while (len--) { *dst++ = src[0] | (src[1] << 8); src += 2; } #else memcpy(dst, src, len * 2); #endif } static inline int fat_get_start(const struct msdos_sb_info *sbi, const struct msdos_dir_entry *de) { int cluster = le16_to_cpu(de->start); if (is_fat32(sbi)) cluster |= (le16_to_cpu(de->starthi) << 16); return cluster; } static inline void fat_set_start(struct msdos_dir_entry *de, int cluster) { de->start = cpu_to_le16(cluster); de->starthi = cpu_to_le16(cluster >> 16); } static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len) { #ifdef __BIG_ENDIAN while (len--) { dst[0] = *src & 0x00FF; dst[1] = (*src & 0xFF00) >> 8; dst += 2; src++; } #else memcpy(dst, src, len * 2); #endif } /* fat/cache.c */ extern void fat_cache_inval_inode(struct inode *inode); extern int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus); extern int fat_get_mapped_cluster(struct inode *inode, sector_t sector, sector_t last_block, unsigned long *mapped_blocks, sector_t *bmap); extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, unsigned long *mapped_blocks, int create, bool from_bmap); /* fat/dir.c */ extern const struct file_operations fat_dir_operations; extern int fat_search_long(struct inode *inode, const unsigned char *name, int name_len, struct fat_slot_info *sinfo); extern int fat_dir_empty(struct inode *dir); extern int fat_subdirs(struct inode *dir); extern int fat_scan(struct inode *dir, const unsigned char *name, struct fat_slot_info *sinfo); extern int fat_scan_logstart(struct inode *dir, int i_logstart, struct fat_slot_info *sinfo); extern int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh, struct msdos_dir_entry **de); extern int fat_alloc_new_dir(struct inode *dir, struct timespec64 *ts); extern int fat_add_entries(struct inode *dir, void *slots, int nr_slots, struct fat_slot_info *sinfo); extern int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo); /* fat/fatent.c */ struct fat_entry { int entry; union { u8 *ent12_p[2]; __le16 *ent16_p; __le32 *ent32_p; } u; int nr_bhs; struct buffer_head *bhs[2]; struct inode *fat_inode; }; static inline void fatent_init(struct fat_entry *fatent) { fatent->nr_bhs = 0; fatent->entry = 0; fatent->u.ent32_p = NULL; fatent->bhs[0] = fatent->bhs[1] = NULL; fatent->fat_inode = NULL; } static inline void fatent_set_entry(struct fat_entry *fatent, int entry) { fatent->entry = entry; fatent->u.ent32_p = NULL; } static inline void fatent_brelse(struct fat_entry *fatent) { int i; fatent->u.ent32_p = NULL; for (i = 0; i < fatent->nr_bhs; i++) brelse(fatent->bhs[i]); fatent->nr_bhs = 0; fatent->bhs[0] = fatent->bhs[1] = NULL; fatent->fat_inode = NULL; } static inline bool fat_valid_entry(struct msdos_sb_info *sbi, int entry) { return FAT_START_ENT <= entry && entry < sbi->max_cluster; } extern void fat_ent_access_init(struct super_block *sb); extern int fat_ent_read(struct inode *inode, struct fat_entry *fatent, int entry); extern int fat_ent_write(struct inode *inode, struct fat_entry *fatent, int new, int wait); extern int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster); extern int fat_free_clusters(struct inode *inode, int cluster); extern int fat_count_free_clusters(struct super_block *sb); extern int fat_trim_fs(struct inode *inode, struct fstrim_range *range); /* fat/file.c */ extern long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); extern const struct file_operations fat_file_operations; extern const struct inode_operations fat_file_inode_operations; extern int fat_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); extern void fat_truncate_blocks(struct inode *inode, loff_t offset); extern int fat_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); extern int fat_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); /* fat/inode.c */ extern int fat_block_truncate_page(struct inode *inode, loff_t from); extern void fat_attach(struct inode *inode, loff_t i_pos); extern void fat_detach(struct inode *inode); extern struct inode *fat_iget(struct super_block *sb, loff_t i_pos); extern struct inode *fat_build_inode(struct super_block *sb, struct msdos_dir_entry *de, loff_t i_pos); extern int fat_sync_inode(struct inode *inode); extern int fat_fill_super(struct super_block *sb, struct fs_context *fc, void (*setup)(struct super_block *)); extern int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de); extern int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2); extern const struct fs_parameter_spec fat_param_spec[]; int fat_init_fs_context(struct fs_context *fc, bool is_vfat); void fat_free_fc(struct fs_context *fc); int fat_parse_param(struct fs_context *fc, struct fs_parameter *param, bool is_vfat); int fat_reconfigure(struct fs_context *fc); static inline unsigned long fat_dir_hash(int logstart) { return hash_32(logstart, FAT_HASH_BITS); } extern int fat_add_cluster(struct inode *inode); /* fat/misc.c */ extern __printf(3, 4) __cold void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...); #define fat_fs_error(sb, fmt, args...) \ __fat_fs_error(sb, 1, fmt , ## args) #define fat_fs_error_ratelimit(sb, fmt, args...) \ __fat_fs_error(sb, __ratelimit(&MSDOS_SB(sb)->ratelimit), fmt , ## args) #define FAT_PRINTK_PREFIX "%sFAT-fs (%s): " #define fat_msg(sb, level, fmt, args...) \ do { \ printk_index_subsys_emit(FAT_PRINTK_PREFIX, level, fmt, ##args);\ _fat_msg(sb, level, fmt, ##args); \ } while (0) __printf(3, 4) __cold void _fat_msg(struct super_block *sb, const char *level, const char *fmt, ...); #define fat_msg_ratelimit(sb, level, fmt, args...) \ do { \ if (__ratelimit(&MSDOS_SB(sb)->ratelimit)) \ fat_msg(sb, level, fmt, ## args); \ } while (0) extern int fat_clusters_flush(struct super_block *sb); extern int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster); extern void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec64 *ts, __le16 __time, __le16 __date, u8 time_cs); extern void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec64 *ts, __le16 *time, __le16 *date, u8 *time_cs); extern struct timespec64 fat_truncate_atime(const struct msdos_sb_info *sbi, const struct timespec64 *ts); extern struct timespec64 fat_truncate_mtime(const struct msdos_sb_info *sbi, const struct timespec64 *ts); extern int fat_truncate_time(struct inode *inode, struct timespec64 *now, int flags); extern int fat_update_time(struct inode *inode, int flags); extern int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs); int fat_cache_init(void); void fat_cache_destroy(void); /* fat/nfs.c */ extern const struct export_operations fat_export_ops; extern const struct export_operations fat_export_ops_nostale; /* helper for printk */ typedef unsigned long long llu; #endif /* !_FAT_H */ |
| 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * drivers/net/macsec.c - MACsec device * * Copyright (c) 2015 Sabrina Dubroca <sd@queasysnail.net> */ #include <linux/types.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/module.h> #include <crypto/aead.h> #include <linux/etherdevice.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> #include <net/genetlink.h> #include <net/sock.h> #include <net/gro_cells.h> #include <net/macsec.h> #include <net/dst_metadata.h> #include <linux/phy.h> #include <linux/byteorder/generic.h> #include <linux/if_arp.h> #include <uapi/linux/if_macsec.h> /* SecTAG length = macsec_eth_header without the optional SCI */ #define MACSEC_TAG_LEN 6 struct macsec_eth_header { struct ethhdr eth; /* SecTAG */ u8 tci_an; #if defined(__LITTLE_ENDIAN_BITFIELD) u8 short_length:6, unused:2; #elif defined(__BIG_ENDIAN_BITFIELD) u8 unused:2, short_length:6; #else #error "Please fix <asm/byteorder.h>" #endif __be32 packet_number; u8 secure_channel_id[8]; /* optional */ } __packed; /* minimum secure data length deemed "not short", see IEEE 802.1AE-2006 9.7 */ #define MIN_NON_SHORT_LEN 48 #define GCM_AES_IV_LEN 12 #define for_each_rxsc(secy, sc) \ for (sc = rcu_dereference_bh(secy->rx_sc); \ sc; \ sc = rcu_dereference_bh(sc->next)) #define for_each_rxsc_rtnl(secy, sc) \ for (sc = rtnl_dereference(secy->rx_sc); \ sc; \ sc = rtnl_dereference(sc->next)) #define pn_same_half(pn1, pn2) (!(((pn1) >> 31) ^ ((pn2) >> 31))) struct gcm_iv_xpn { union { u8 short_secure_channel_id[4]; ssci_t ssci; }; __be64 pn; } __packed; struct gcm_iv { union { u8 secure_channel_id[8]; sci_t sci; }; __be32 pn; }; #define MACSEC_VALIDATE_DEFAULT MACSEC_VALIDATE_STRICT struct pcpu_secy_stats { struct macsec_dev_stats stats; struct u64_stats_sync syncp; }; /** * struct macsec_dev - private data * @secy: SecY config * @real_dev: pointer to underlying netdevice * @dev_tracker: refcount tracker for @real_dev reference * @stats: MACsec device stats * @secys: linked list of SecY's on the underlying device * @gro_cells: pointer to the Generic Receive Offload cell * @offload: status of offloading on the MACsec device * @insert_tx_tag: when offloading, device requires to insert an * additional tag */ struct macsec_dev { struct macsec_secy secy; struct net_device *real_dev; netdevice_tracker dev_tracker; struct pcpu_secy_stats __percpu *stats; struct list_head secys; struct gro_cells gro_cells; enum macsec_offload offload; bool insert_tx_tag; }; /** * struct macsec_rxh_data - rx_handler private argument * @secys: linked list of SecY's on this underlying device */ struct macsec_rxh_data { struct list_head secys; }; static struct macsec_dev *macsec_priv(const struct net_device *dev) { return (struct macsec_dev *)netdev_priv(dev); } static struct macsec_rxh_data *macsec_data_rcu(const struct net_device *dev) { return rcu_dereference_bh(dev->rx_handler_data); } static struct macsec_rxh_data *macsec_data_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->rx_handler_data); } struct macsec_cb { struct aead_request *req; union { struct macsec_tx_sa *tx_sa; struct macsec_rx_sa *rx_sa; }; u8 assoc_num; bool valid; bool has_sci; }; static struct macsec_rx_sa *macsec_rxsa_get(struct macsec_rx_sa __rcu *ptr) { struct macsec_rx_sa *sa = rcu_dereference_bh(ptr); if (!sa || !sa->active) return NULL; if (!refcount_inc_not_zero(&sa->refcnt)) return NULL; return sa; } static struct macsec_rx_sa *macsec_active_rxsa_get(struct macsec_rx_sc *rx_sc) { struct macsec_rx_sa *sa = NULL; int an; for (an = 0; an < MACSEC_NUM_AN; an++) { sa = macsec_rxsa_get(rx_sc->sa[an]); if (sa) break; } return sa; } static void free_rx_sc_rcu(struct rcu_head *head) { struct macsec_rx_sc *rx_sc = container_of(head, struct macsec_rx_sc, rcu_head); free_percpu(rx_sc->stats); kfree(rx_sc); } static struct macsec_rx_sc *macsec_rxsc_get(struct macsec_rx_sc *sc) { return refcount_inc_not_zero(&sc->refcnt) ? sc : NULL; } static void macsec_rxsc_put(struct macsec_rx_sc *sc) { if (refcount_dec_and_test(&sc->refcnt)) call_rcu(&sc->rcu_head, free_rx_sc_rcu); } static void free_rxsa(struct rcu_head *head) { struct macsec_rx_sa *sa = container_of(head, struct macsec_rx_sa, rcu); crypto_free_aead(sa->key.tfm); free_percpu(sa->stats); kfree(sa); } static void macsec_rxsa_put(struct macsec_rx_sa *sa) { if (refcount_dec_and_test(&sa->refcnt)) call_rcu(&sa->rcu, free_rxsa); } static struct macsec_tx_sa *macsec_txsa_get(struct macsec_tx_sa __rcu *ptr) { struct macsec_tx_sa *sa = rcu_dereference_bh(ptr); if (!sa || !sa->active) return NULL; if (!refcount_inc_not_zero(&sa->refcnt)) return NULL; return sa; } static void free_txsa(struct rcu_head *head) { struct macsec_tx_sa *sa = container_of(head, struct macsec_tx_sa, rcu); crypto_free_aead(sa->key.tfm); free_percpu(sa->stats); kfree(sa); } static void macsec_txsa_put(struct macsec_tx_sa *sa) { if (refcount_dec_and_test(&sa->refcnt)) call_rcu(&sa->rcu, free_txsa); } static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct macsec_cb) > sizeof(skb->cb)); return (struct macsec_cb *)skb->cb; } #define MACSEC_PORT_SCB (0x0000) #define MACSEC_UNDEF_SCI ((__force sci_t)0xffffffffffffffffULL) #define MACSEC_UNDEF_SSCI ((__force ssci_t)0xffffffff) #define MACSEC_GCM_AES_128_SAK_LEN 16 #define MACSEC_GCM_AES_256_SAK_LEN 32 #define DEFAULT_SAK_LEN MACSEC_GCM_AES_128_SAK_LEN #define DEFAULT_XPN false #define DEFAULT_SEND_SCI true #define DEFAULT_ENCRYPT false #define DEFAULT_ENCODING_SA 0 #define MACSEC_XPN_MAX_REPLAY_WINDOW (((1 << 30) - 1)) static sci_t make_sci(const u8 *addr, __be16 port) { sci_t sci; memcpy(&sci, addr, ETH_ALEN); memcpy(((char *)&sci) + ETH_ALEN, &port, sizeof(port)); return sci; } static sci_t macsec_frame_sci(struct macsec_eth_header *hdr, bool sci_present) { sci_t sci; if (sci_present) memcpy(&sci, hdr->secure_channel_id, sizeof(hdr->secure_channel_id)); else sci = make_sci(hdr->eth.h_source, MACSEC_PORT_ES); return sci; } static unsigned int macsec_sectag_len(bool sci_present) { return MACSEC_TAG_LEN + (sci_present ? MACSEC_SCI_LEN : 0); } static unsigned int macsec_hdr_len(bool sci_present) { return macsec_sectag_len(sci_present) + ETH_HLEN; } static unsigned int macsec_extra_len(bool sci_present) { return macsec_sectag_len(sci_present) + sizeof(__be16); } /* Fill SecTAG according to IEEE 802.1AE-2006 10.5.3 */ static void macsec_fill_sectag(struct macsec_eth_header *h, const struct macsec_secy *secy, u32 pn, bool sci_present) { const struct macsec_tx_sc *tx_sc = &secy->tx_sc; memset(&h->tci_an, 0, macsec_sectag_len(sci_present)); h->eth.h_proto = htons(ETH_P_MACSEC); if (sci_present) { h->tci_an |= MACSEC_TCI_SC; memcpy(&h->secure_channel_id, &secy->sci, sizeof(h->secure_channel_id)); } else { if (tx_sc->end_station) h->tci_an |= MACSEC_TCI_ES; if (tx_sc->scb) h->tci_an |= MACSEC_TCI_SCB; } h->packet_number = htonl(pn); /* with GCM, C/E clear for !encrypt, both set for encrypt */ if (tx_sc->encrypt) h->tci_an |= MACSEC_TCI_CONFID; else if (secy->icv_len != MACSEC_DEFAULT_ICV_LEN) h->tci_an |= MACSEC_TCI_C; h->tci_an |= tx_sc->encoding_sa; } static void macsec_set_shortlen(struct macsec_eth_header *h, size_t data_len) { if (data_len < MIN_NON_SHORT_LEN) h->short_length = data_len; } /* Checks if a MACsec interface is being offloaded to an hardware engine */ static bool macsec_is_offloaded(struct macsec_dev *macsec) { if (macsec->offload == MACSEC_OFFLOAD_MAC || macsec->offload == MACSEC_OFFLOAD_PHY) return true; return false; } /* Checks if underlying layers implement MACsec offloading functions. */ static bool macsec_check_offload(enum macsec_offload offload, struct macsec_dev *macsec) { if (!macsec || !macsec->real_dev) return false; if (offload == MACSEC_OFFLOAD_PHY) return macsec->real_dev->phydev && macsec->real_dev->phydev->macsec_ops; else if (offload == MACSEC_OFFLOAD_MAC) return macsec->real_dev->features & NETIF_F_HW_MACSEC && macsec->real_dev->macsec_ops; return false; } static const struct macsec_ops *__macsec_get_ops(enum macsec_offload offload, struct macsec_dev *macsec, struct macsec_context *ctx) { if (ctx) { memset(ctx, 0, sizeof(*ctx)); ctx->offload = offload; if (offload == MACSEC_OFFLOAD_PHY) ctx->phydev = macsec->real_dev->phydev; else if (offload == MACSEC_OFFLOAD_MAC) ctx->netdev = macsec->real_dev; } if (offload == MACSEC_OFFLOAD_PHY) return macsec->real_dev->phydev->macsec_ops; else return macsec->real_dev->macsec_ops; } /* Returns a pointer to the MACsec ops struct if any and updates the MACsec * context device reference if provided. */ static const struct macsec_ops *macsec_get_ops(struct macsec_dev *macsec, struct macsec_context *ctx) { if (!macsec_check_offload(macsec->offload, macsec)) return NULL; return __macsec_get_ops(macsec->offload, macsec, ctx); } /* validate MACsec packet according to IEEE 802.1AE-2018 9.12 */ static bool macsec_validate_skb(struct sk_buff *skb, u16 icv_len, bool xpn) { struct macsec_eth_header *h = (struct macsec_eth_header *)skb->data; int len = skb->len - 2 * ETH_ALEN; int extra_len = macsec_extra_len(!!(h->tci_an & MACSEC_TCI_SC)) + icv_len; /* a) It comprises at least 17 octets */ if (skb->len <= 16) return false; /* b) MACsec EtherType: already checked */ /* c) V bit is clear */ if (h->tci_an & MACSEC_TCI_VERSION) return false; /* d) ES or SCB => !SC */ if ((h->tci_an & MACSEC_TCI_ES || h->tci_an & MACSEC_TCI_SCB) && (h->tci_an & MACSEC_TCI_SC)) return false; /* e) Bits 7 and 8 of octet 4 of the SecTAG are clear */ if (h->unused) return false; /* rx.pn != 0 if not XPN (figure 10-5 with 802.11AEbw-2013 amendment) */ if (!h->packet_number && !xpn) return false; /* length check, f) g) h) i) */ if (h->short_length) return len == extra_len + h->short_length; return len >= extra_len + MIN_NON_SHORT_LEN; } #define MACSEC_NEEDED_HEADROOM (macsec_extra_len(true)) #define MACSEC_NEEDED_TAILROOM MACSEC_STD_ICV_LEN static void macsec_fill_iv_xpn(unsigned char *iv, ssci_t ssci, u64 pn, salt_t salt) { struct gcm_iv_xpn *gcm_iv = (struct gcm_iv_xpn *)iv; gcm_iv->ssci = ssci ^ salt.ssci; gcm_iv->pn = cpu_to_be64(pn) ^ salt.pn; } static void macsec_fill_iv(unsigned char *iv, sci_t sci, u32 pn) { struct gcm_iv *gcm_iv = (struct gcm_iv *)iv; gcm_iv->sci = sci; gcm_iv->pn = htonl(pn); } static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb) { return (struct macsec_eth_header *)skb_mac_header(skb); } static void __macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa) { pr_debug("PN wrapped, transitioning to !oper\n"); tx_sa->active = false; if (secy->protect_frames) secy->operational = false; } void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa) { spin_lock_bh(&tx_sa->lock); __macsec_pn_wrapped(secy, tx_sa); spin_unlock_bh(&tx_sa->lock); } EXPORT_SYMBOL_GPL(macsec_pn_wrapped); static pn_t tx_sa_update_pn(struct macsec_tx_sa *tx_sa, struct macsec_secy *secy) { pn_t pn; spin_lock_bh(&tx_sa->lock); pn = tx_sa->next_pn_halves; if (secy->xpn) tx_sa->next_pn++; else tx_sa->next_pn_halves.lower++; if (tx_sa->next_pn == 0) __macsec_pn_wrapped(secy, tx_sa); spin_unlock_bh(&tx_sa->lock); return pn; } static void macsec_encrypt_finish(struct sk_buff *skb, struct net_device *dev) { struct macsec_dev *macsec = netdev_priv(dev); skb->dev = macsec->real_dev; skb_reset_mac_header(skb); skb->protocol = eth_hdr(skb)->h_proto; } static unsigned int macsec_msdu_len(struct sk_buff *skb) { struct macsec_dev *macsec = macsec_priv(skb->dev); struct macsec_secy *secy = &macsec->secy; bool sci_present = macsec_skb_cb(skb)->has_sci; return skb->len - macsec_hdr_len(sci_present) - secy->icv_len; } static void macsec_count_tx(struct sk_buff *skb, struct macsec_tx_sc *tx_sc, struct macsec_tx_sa *tx_sa) { unsigned int msdu_len = macsec_msdu_len(skb); struct pcpu_tx_sc_stats *txsc_stats = this_cpu_ptr(tx_sc->stats); u64_stats_update_begin(&txsc_stats->syncp); if (tx_sc->encrypt) { txsc_stats->stats.OutOctetsEncrypted += msdu_len; txsc_stats->stats.OutPktsEncrypted++; this_cpu_inc(tx_sa->stats->OutPktsEncrypted); } else { txsc_stats->stats.OutOctetsProtected += msdu_len; txsc_stats->stats.OutPktsProtected++; this_cpu_inc(tx_sa->stats->OutPktsProtected); } u64_stats_update_end(&txsc_stats->syncp); } static void count_tx(struct net_device *dev, int ret, int len) { if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) dev_sw_netstats_tx_add(dev, 1, len); } static void macsec_encrypt_done(void *data, int err) { struct sk_buff *skb = data; struct net_device *dev = skb->dev; struct macsec_dev *macsec = macsec_priv(dev); struct macsec_tx_sa *sa = macsec_skb_cb(skb)->tx_sa; int len, ret; aead_request_free(macsec_skb_cb(skb)->req); rcu_read_lock_bh(); macsec_count_tx(skb, &macsec->secy.tx_sc, macsec_skb_cb(skb)->tx_sa); /* packet is encrypted/protected so tx_bytes must be calculated */ len = macsec_msdu_len(skb) + 2 * ETH_ALEN; macsec_encrypt_finish(skb, dev); ret = dev_queue_xmit(skb); count_tx(dev, ret, len); rcu_read_unlock_bh(); macsec_txsa_put(sa); dev_put(dev); } static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm, unsigned char **iv, struct scatterlist **sg, int num_frags) { size_t size, iv_offset, sg_offset; struct aead_request *req; void *tmp; size = sizeof(struct aead_request) + crypto_aead_reqsize(tfm); iv_offset = size; size += GCM_AES_IV_LEN; size = ALIGN(size, __alignof__(struct scatterlist)); sg_offset = size; size += sizeof(struct scatterlist) * num_frags; tmp = kmalloc(size, GFP_ATOMIC); if (!tmp) return NULL; *iv = (unsigned char *)(tmp + iv_offset); *sg = (struct scatterlist *)(tmp + sg_offset); req = tmp; aead_request_set_tfm(req, tfm); return req; } static struct sk_buff *macsec_encrypt(struct sk_buff *skb, struct net_device *dev) { int ret; struct scatterlist *sg; struct sk_buff *trailer; unsigned char *iv; struct ethhdr *eth; struct macsec_eth_header *hh; size_t unprotected_len; struct aead_request *req; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; struct macsec_dev *macsec = macsec_priv(dev); bool sci_present; pn_t pn; secy = &macsec->secy; tx_sc = &secy->tx_sc; /* 10.5.1 TX SA assignment */ tx_sa = macsec_txsa_get(tx_sc->sa[tx_sc->encoding_sa]); if (!tx_sa) { secy->operational = false; kfree_skb(skb); return ERR_PTR(-EINVAL); } if (unlikely(skb_headroom(skb) < MACSEC_NEEDED_HEADROOM || skb_tailroom(skb) < MACSEC_NEEDED_TAILROOM)) { struct sk_buff *nskb = skb_copy_expand(skb, MACSEC_NEEDED_HEADROOM, MACSEC_NEEDED_TAILROOM, GFP_ATOMIC); if (likely(nskb)) { consume_skb(skb); skb = nskb; } else { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-ENOMEM); } } else { skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) { macsec_txsa_put(tx_sa); return ERR_PTR(-ENOMEM); } } unprotected_len = skb->len; eth = eth_hdr(skb); sci_present = macsec_send_sci(secy); hh = skb_push(skb, macsec_extra_len(sci_present)); memmove(hh, eth, 2 * ETH_ALEN); pn = tx_sa_update_pn(tx_sa, secy); if (pn.full64 == 0) { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-ENOLINK); } macsec_fill_sectag(hh, secy, pn.lower, sci_present); macsec_set_shortlen(hh, unprotected_len - 2 * ETH_ALEN); skb_put(skb, secy->icv_len); if (skb->len - ETH_HLEN > macsec_priv(dev)->real_dev->mtu) { struct pcpu_secy_stats *secy_stats = this_cpu_ptr(macsec->stats); u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.OutPktsTooLong++; u64_stats_update_end(&secy_stats->syncp); macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-EINVAL); } ret = skb_cow_data(skb, 0, &trailer); if (unlikely(ret < 0)) { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(ret); } req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg, ret); if (!req) { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-ENOMEM); } if (secy->xpn) macsec_fill_iv_xpn(iv, tx_sa->ssci, pn.full64, tx_sa->key.salt); else macsec_fill_iv(iv, secy->sci, pn.lower); sg_init_table(sg, ret); ret = skb_to_sgvec(skb, sg, 0, skb->len); if (unlikely(ret < 0)) { aead_request_free(req); macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(ret); } if (tx_sc->encrypt) { int len = skb->len - macsec_hdr_len(sci_present) - secy->icv_len; aead_request_set_crypt(req, sg, sg, len, iv); aead_request_set_ad(req, macsec_hdr_len(sci_present)); } else { aead_request_set_crypt(req, sg, sg, 0, iv); aead_request_set_ad(req, skb->len - secy->icv_len); } macsec_skb_cb(skb)->req = req; macsec_skb_cb(skb)->tx_sa = tx_sa; macsec_skb_cb(skb)->has_sci = sci_present; aead_request_set_callback(req, 0, macsec_encrypt_done, skb); dev_hold(skb->dev); ret = crypto_aead_encrypt(req); if (ret == -EINPROGRESS) { return ERR_PTR(ret); } else if (ret != 0) { dev_put(skb->dev); kfree_skb(skb); aead_request_free(req); macsec_txsa_put(tx_sa); return ERR_PTR(-EINVAL); } dev_put(skb->dev); aead_request_free(req); macsec_txsa_put(tx_sa); return skb; } static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u32 pn) { struct macsec_rx_sa *rx_sa = macsec_skb_cb(skb)->rx_sa; struct pcpu_rx_sc_stats *rxsc_stats = this_cpu_ptr(rx_sa->sc->stats); struct macsec_eth_header *hdr = macsec_ethhdr(skb); u32 lowest_pn = 0; spin_lock(&rx_sa->lock); if (rx_sa->next_pn_halves.lower >= secy->replay_window) lowest_pn = rx_sa->next_pn_halves.lower - secy->replay_window; /* Now perform replay protection check again * (see IEEE 802.1AE-2006 figure 10-5) */ if (secy->replay_protect && pn < lowest_pn && (!secy->xpn || pn_same_half(pn, lowest_pn))) { spin_unlock(&rx_sa->lock); u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); DEV_STATS_INC(secy->netdev, rx_dropped); return false; } if (secy->validate_frames != MACSEC_VALIDATE_DISABLED) { unsigned int msdu_len = macsec_msdu_len(skb); u64_stats_update_begin(&rxsc_stats->syncp); if (hdr->tci_an & MACSEC_TCI_E) rxsc_stats->stats.InOctetsDecrypted += msdu_len; else rxsc_stats->stats.InOctetsValidated += msdu_len; u64_stats_update_end(&rxsc_stats->syncp); } if (!macsec_skb_cb(skb)->valid) { spin_unlock(&rx_sa->lock); /* 10.6.5 */ if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotValid++; u64_stats_update_end(&rxsc_stats->syncp); this_cpu_inc(rx_sa->stats->InPktsNotValid); DEV_STATS_INC(secy->netdev, rx_errors); return false; } u64_stats_update_begin(&rxsc_stats->syncp); if (secy->validate_frames == MACSEC_VALIDATE_CHECK) { rxsc_stats->stats.InPktsInvalid++; this_cpu_inc(rx_sa->stats->InPktsInvalid); } else if (pn < lowest_pn) { rxsc_stats->stats.InPktsDelayed++; } else { rxsc_stats->stats.InPktsUnchecked++; } u64_stats_update_end(&rxsc_stats->syncp); } else { u64_stats_update_begin(&rxsc_stats->syncp); if (pn < lowest_pn) { rxsc_stats->stats.InPktsDelayed++; } else { rxsc_stats->stats.InPktsOK++; this_cpu_inc(rx_sa->stats->InPktsOK); } u64_stats_update_end(&rxsc_stats->syncp); // Instead of "pn >=" - to support pn overflow in xpn if (pn + 1 > rx_sa->next_pn_halves.lower) { rx_sa->next_pn_halves.lower = pn + 1; } else if (secy->xpn && !pn_same_half(pn, rx_sa->next_pn_halves.lower)) { rx_sa->next_pn_halves.upper++; rx_sa->next_pn_halves.lower = pn + 1; } spin_unlock(&rx_sa->lock); } return true; } static void macsec_reset_skb(struct sk_buff *skb, struct net_device *dev) { skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, dev); skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb); } static void macsec_finalize_skb(struct sk_buff *skb, u8 icv_len, u8 hdr_len) { skb->ip_summed = CHECKSUM_NONE; memmove(skb->data + hdr_len, skb->data, 2 * ETH_ALEN); skb_pull(skb, hdr_len); pskb_trim_unique(skb, skb->len - icv_len); } static void count_rx(struct net_device *dev, int len) { dev_sw_netstats_rx_add(dev, len); } static void macsec_decrypt_done(void *data, int err) { struct sk_buff *skb = data; struct net_device *dev = skb->dev; struct macsec_dev *macsec = macsec_priv(dev); struct macsec_rx_sa *rx_sa = macsec_skb_cb(skb)->rx_sa; struct macsec_rx_sc *rx_sc = rx_sa->sc; int len; u32 pn; aead_request_free(macsec_skb_cb(skb)->req); if (!err) macsec_skb_cb(skb)->valid = true; rcu_read_lock_bh(); pn = ntohl(macsec_ethhdr(skb)->packet_number); if (!macsec_post_decrypt(skb, &macsec->secy, pn)) { rcu_read_unlock_bh(); kfree_skb(skb); goto out; } macsec_finalize_skb(skb, macsec->secy.icv_len, macsec_extra_len(macsec_skb_cb(skb)->has_sci)); len = skb->len; macsec_reset_skb(skb, macsec->secy.netdev); if (gro_cells_receive(&macsec->gro_cells, skb) == NET_RX_SUCCESS) count_rx(dev, len); rcu_read_unlock_bh(); out: macsec_rxsa_put(rx_sa); macsec_rxsc_put(rx_sc); dev_put(dev); } static struct sk_buff *macsec_decrypt(struct sk_buff *skb, struct net_device *dev, struct macsec_rx_sa *rx_sa, sci_t sci, struct macsec_secy *secy) { int ret; struct scatterlist *sg; struct sk_buff *trailer; unsigned char *iv; struct aead_request *req; struct macsec_eth_header *hdr; u32 hdr_pn; u16 icv_len = secy->icv_len; macsec_skb_cb(skb)->valid = false; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return ERR_PTR(-ENOMEM); ret = skb_cow_data(skb, 0, &trailer); if (unlikely(ret < 0)) { kfree_skb(skb); return ERR_PTR(ret); } req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg, ret); if (!req) { kfree_skb(skb); return ERR_PTR(-ENOMEM); } hdr = (struct macsec_eth_header *)skb->data; hdr_pn = ntohl(hdr->packet_number); if (secy->xpn) { pn_t recovered_pn = rx_sa->next_pn_halves; recovered_pn.lower = hdr_pn; if (hdr_pn < rx_sa->next_pn_halves.lower && !pn_same_half(hdr_pn, rx_sa->next_pn_halves.lower)) recovered_pn.upper++; macsec_fill_iv_xpn(iv, rx_sa->ssci, recovered_pn.full64, rx_sa->key.salt); } else { macsec_fill_iv(iv, sci, hdr_pn); } sg_init_table(sg, ret); ret = skb_to_sgvec(skb, sg, 0, skb->len); if (unlikely(ret < 0)) { aead_request_free(req); kfree_skb(skb); return ERR_PTR(ret); } if (hdr->tci_an & MACSEC_TCI_E) { /* confidentiality: ethernet + macsec header * authenticated, encrypted payload */ int len = skb->len - macsec_hdr_len(macsec_skb_cb(skb)->has_sci); aead_request_set_crypt(req, sg, sg, len, iv); aead_request_set_ad(req, macsec_hdr_len(macsec_skb_cb(skb)->has_sci)); skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) { aead_request_free(req); return ERR_PTR(-ENOMEM); } } else { /* integrity only: all headers + data authenticated */ aead_request_set_crypt(req, sg, sg, icv_len, iv); aead_request_set_ad(req, skb->len - icv_len); } macsec_skb_cb(skb)->req = req; skb->dev = dev; aead_request_set_callback(req, 0, macsec_decrypt_done, skb); dev_hold(dev); ret = crypto_aead_decrypt(req); if (ret == -EINPROGRESS) { return ERR_PTR(ret); } else if (ret != 0) { /* decryption/authentication failed * 10.6 if validateFrames is disabled, deliver anyway */ if (ret != -EBADMSG) { kfree_skb(skb); skb = ERR_PTR(ret); } } else { macsec_skb_cb(skb)->valid = true; } dev_put(dev); aead_request_free(req); return skb; } static struct macsec_rx_sc *find_rx_sc(struct macsec_secy *secy, sci_t sci) { struct macsec_rx_sc *rx_sc; for_each_rxsc(secy, rx_sc) { if (rx_sc->sci == sci) return rx_sc; } return NULL; } static struct macsec_rx_sc *find_rx_sc_rtnl(struct macsec_secy *secy, sci_t sci) { struct macsec_rx_sc *rx_sc; for_each_rxsc_rtnl(secy, rx_sc) { if (rx_sc->sci == sci) return rx_sc; } return NULL; } static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) { /* Deliver to the uncontrolled port by default */ enum rx_handler_result ret = RX_HANDLER_PASS; struct ethhdr *hdr = eth_hdr(skb); struct metadata_dst *md_dst; struct macsec_rxh_data *rxd; struct macsec_dev *macsec; bool is_macsec_md_dst; rcu_read_lock(); rxd = macsec_data_rcu(skb->dev); md_dst = skb_metadata_dst(skb); is_macsec_md_dst = md_dst && md_dst->type == METADATA_MACSEC; list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct sk_buff *nskb; struct pcpu_secy_stats *secy_stats = this_cpu_ptr(macsec->stats); struct net_device *ndev = macsec->secy.netdev; /* If h/w offloading is enabled, HW decodes frames and strips * the SecTAG, so we have to deduce which port to deliver to. */ if (macsec_is_offloaded(macsec) && netif_running(ndev)) { const struct macsec_ops *ops; ops = macsec_get_ops(macsec, NULL); if (ops->rx_uses_md_dst && !is_macsec_md_dst) continue; if (is_macsec_md_dst) { struct macsec_rx_sc *rx_sc; /* All drivers that implement MACsec offload * support using skb metadata destinations must * indicate that they do so. */ DEBUG_NET_WARN_ON_ONCE(!ops->rx_uses_md_dst); rx_sc = find_rx_sc(&macsec->secy, md_dst->u.macsec_info.sci); if (!rx_sc) continue; /* device indicated macsec offload occurred */ skb->dev = ndev; skb->pkt_type = PACKET_HOST; eth_skb_pkt_type(skb, ndev); ret = RX_HANDLER_ANOTHER; goto out; } /* This datapath is insecure because it is unable to * enforce isolation of broadcast/multicast traffic and * unicast traffic with promiscuous mode on the macsec * netdev. Since the core stack has no mechanism to * check that the hardware did indeed receive MACsec * traffic, it is possible that the response handling * done by the MACsec port was to a plaintext packet. * This violates the MACsec protocol standard. */ if (ether_addr_equal_64bits(hdr->h_dest, ndev->dev_addr)) { /* exact match, divert skb to this port */ skb->dev = ndev; skb->pkt_type = PACKET_HOST; ret = RX_HANDLER_ANOTHER; goto out; } else if (is_multicast_ether_addr_64bits( hdr->h_dest)) { /* multicast frame, deliver on this port too */ nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) break; nskb->dev = ndev; eth_skb_pkt_type(nskb, ndev); __netif_rx(nskb); } else if (ndev->flags & IFF_PROMISC) { skb->dev = ndev; skb->pkt_type = PACKET_HOST; ret = RX_HANDLER_ANOTHER; goto out; } continue; } /* 10.6 If the management control validateFrames is not * Strict, frames without a SecTAG are received, counted, and * delivered to the Controlled Port */ if (macsec->secy.validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoTag++; u64_stats_update_end(&secy_stats->syncp); DEV_STATS_INC(macsec->secy.netdev, rx_dropped); continue; } /* deliver on this port */ nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) break; nskb->dev = ndev; if (__netif_rx(nskb) == NET_RX_SUCCESS) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsUntagged++; u64_stats_update_end(&secy_stats->syncp); } } out: rcu_read_unlock(); return ret; } static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct net_device *dev = skb->dev; struct macsec_eth_header *hdr; struct macsec_secy *secy = NULL; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; struct macsec_rxh_data *rxd; struct macsec_dev *macsec; unsigned int len; sci_t sci; u32 hdr_pn; bool cbit; struct pcpu_rx_sc_stats *rxsc_stats; struct pcpu_secy_stats *secy_stats; bool pulled_sci; int ret; if (skb_headroom(skb) < ETH_HLEN) goto drop_direct; hdr = macsec_ethhdr(skb); if (hdr->eth.h_proto != htons(ETH_P_MACSEC)) return handle_not_macsec(skb); skb = skb_unshare(skb, GFP_ATOMIC); *pskb = skb; if (!skb) return RX_HANDLER_CONSUMED; pulled_sci = pskb_may_pull(skb, macsec_extra_len(true)); if (!pulled_sci) { if (!pskb_may_pull(skb, macsec_extra_len(false))) goto drop_direct; } hdr = macsec_ethhdr(skb); /* Frames with a SecTAG that has the TCI E bit set but the C * bit clear are discarded, as this reserved encoding is used * to identify frames with a SecTAG that are not to be * delivered to the Controlled Port. */ if ((hdr->tci_an & (MACSEC_TCI_C | MACSEC_TCI_E)) == MACSEC_TCI_E) return RX_HANDLER_PASS; /* now, pull the extra length */ if (hdr->tci_an & MACSEC_TCI_SC) { if (!pulled_sci) goto drop_direct; } /* ethernet header is part of crypto processing */ skb_push(skb, ETH_HLEN); macsec_skb_cb(skb)->has_sci = !!(hdr->tci_an & MACSEC_TCI_SC); macsec_skb_cb(skb)->assoc_num = hdr->tci_an & MACSEC_AN_MASK; sci = macsec_frame_sci(hdr, macsec_skb_cb(skb)->has_sci); rcu_read_lock(); rxd = macsec_data_rcu(skb->dev); list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct macsec_rx_sc *sc = find_rx_sc(&macsec->secy, sci); sc = sc ? macsec_rxsc_get(sc) : NULL; if (sc) { secy = &macsec->secy; rx_sc = sc; break; } } if (!secy) goto nosci; dev = secy->netdev; macsec = macsec_priv(dev); secy_stats = this_cpu_ptr(macsec->stats); rxsc_stats = this_cpu_ptr(rx_sc->stats); if (!macsec_validate_skb(skb, secy->icv_len, secy->xpn)) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsBadTag++; u64_stats_update_end(&secy_stats->syncp); DEV_STATS_INC(secy->netdev, rx_errors); goto drop_nosa; } rx_sa = macsec_rxsa_get(rx_sc->sa[macsec_skb_cb(skb)->assoc_num]); if (!rx_sa) { /* 10.6.1 if the SA is not in use */ /* If validateFrames is Strict or the C bit in the * SecTAG is set, discard */ struct macsec_rx_sa *active_rx_sa = macsec_active_rxsa_get(rx_sc); if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotUsingSA++; u64_stats_update_end(&rxsc_stats->syncp); DEV_STATS_INC(secy->netdev, rx_errors); if (active_rx_sa) this_cpu_inc(active_rx_sa->stats->InPktsNotUsingSA); goto drop_nosa; } /* not Strict, the frame (with the SecTAG and ICV * removed) is delivered to the Controlled Port. */ u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsUnusedSA++; u64_stats_update_end(&rxsc_stats->syncp); if (active_rx_sa) this_cpu_inc(active_rx_sa->stats->InPktsUnusedSA); goto deliver; } /* First, PN check to avoid decrypting obviously wrong packets */ hdr_pn = ntohl(hdr->packet_number); if (secy->replay_protect) { bool late; spin_lock(&rx_sa->lock); late = rx_sa->next_pn_halves.lower >= secy->replay_window && hdr_pn < (rx_sa->next_pn_halves.lower - secy->replay_window); if (secy->xpn) late = late && pn_same_half(rx_sa->next_pn_halves.lower, hdr_pn); spin_unlock(&rx_sa->lock); if (late) { u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); DEV_STATS_INC(macsec->secy.netdev, rx_dropped); goto drop; } } macsec_skb_cb(skb)->rx_sa = rx_sa; /* Disabled && !changed text => skip validation */ if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames != MACSEC_VALIDATE_DISABLED) skb = macsec_decrypt(skb, dev, rx_sa, sci, secy); if (IS_ERR(skb)) { /* the decrypt callback needs the reference */ if (PTR_ERR(skb) != -EINPROGRESS) { macsec_rxsa_put(rx_sa); macsec_rxsc_put(rx_sc); } rcu_read_unlock(); *pskb = NULL; return RX_HANDLER_CONSUMED; } if (!macsec_post_decrypt(skb, secy, hdr_pn)) goto drop; deliver: macsec_finalize_skb(skb, secy->icv_len, macsec_extra_len(macsec_skb_cb(skb)->has_sci)); len = skb->len; macsec_reset_skb(skb, secy->netdev); if (rx_sa) macsec_rxsa_put(rx_sa); macsec_rxsc_put(rx_sc); skb_orphan(skb); ret = gro_cells_receive(&macsec->gro_cells, skb); if (ret == NET_RX_SUCCESS) count_rx(dev, len); else DEV_STATS_INC(macsec->secy.netdev, rx_dropped); rcu_read_unlock(); *pskb = NULL; return RX_HANDLER_CONSUMED; drop: macsec_rxsa_put(rx_sa); drop_nosa: macsec_rxsc_put(rx_sc); rcu_read_unlock(); drop_direct: kfree_skb(skb); *pskb = NULL; return RX_HANDLER_CONSUMED; nosci: /* 10.6.1 if the SC is not found */ cbit = !!(hdr->tci_an & MACSEC_TCI_C); if (!cbit) macsec_finalize_skb(skb, MACSEC_DEFAULT_ICV_LEN, macsec_extra_len(macsec_skb_cb(skb)->has_sci)); list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct sk_buff *nskb; secy_stats = this_cpu_ptr(macsec->stats); /* If validateFrames is Strict or the C bit in the * SecTAG is set, discard */ if (cbit || macsec->secy.validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoSCI++; u64_stats_update_end(&secy_stats->syncp); DEV_STATS_INC(macsec->secy.netdev, rx_errors); continue; } /* not strict, the frame (with the SecTAG and ICV * removed) is delivered to the Controlled Port. */ nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) break; macsec_reset_skb(nskb, macsec->secy.netdev); ret = __netif_rx(nskb); if (ret == NET_RX_SUCCESS) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsUnknownSCI++; u64_stats_update_end(&secy_stats->syncp); } else { DEV_STATS_INC(macsec->secy.netdev, rx_dropped); } } rcu_read_unlock(); *pskb = skb; return RX_HANDLER_PASS; } static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len) { struct crypto_aead *tfm; int ret; tfm = crypto_alloc_aead("gcm(aes)", 0, 0); if (IS_ERR(tfm)) return tfm; ret = crypto_aead_setkey(tfm, key, key_len); if (ret < 0) goto fail; ret = crypto_aead_setauthsize(tfm, icv_len); if (ret < 0) goto fail; return tfm; fail: crypto_free_aead(tfm); return ERR_PTR(ret); } static int init_rx_sa(struct macsec_rx_sa *rx_sa, char *sak, int key_len, int icv_len) { rx_sa->stats = alloc_percpu(struct macsec_rx_sa_stats); if (!rx_sa->stats) return -ENOMEM; rx_sa->key.tfm = macsec_alloc_tfm(sak, key_len, icv_len); if (IS_ERR(rx_sa->key.tfm)) { free_percpu(rx_sa->stats); return PTR_ERR(rx_sa->key.tfm); } rx_sa->ssci = MACSEC_UNDEF_SSCI; rx_sa->active = false; rx_sa->next_pn = 1; refcount_set(&rx_sa->refcnt, 1); spin_lock_init(&rx_sa->lock); return 0; } static void clear_rx_sa(struct macsec_rx_sa *rx_sa) { rx_sa->active = false; macsec_rxsa_put(rx_sa); } static void free_rx_sc(struct macsec_rx_sc *rx_sc) { int i; for (i = 0; i < MACSEC_NUM_AN; i++) { struct macsec_rx_sa *sa = rtnl_dereference(rx_sc->sa[i]); RCU_INIT_POINTER(rx_sc->sa[i], NULL); if (sa) clear_rx_sa(sa); } macsec_rxsc_put(rx_sc); } static struct macsec_rx_sc *del_rx_sc(struct macsec_secy *secy, sci_t sci) { struct macsec_rx_sc *rx_sc, __rcu **rx_scp; for (rx_scp = &secy->rx_sc, rx_sc = rtnl_dereference(*rx_scp); rx_sc; rx_scp = &rx_sc->next, rx_sc = rtnl_dereference(*rx_scp)) { if (rx_sc->sci == sci) { if (rx_sc->active) secy->n_rx_sc--; rcu_assign_pointer(*rx_scp, rx_sc->next); return rx_sc; } } return NULL; } static struct macsec_rx_sc *create_rx_sc(struct net_device *dev, sci_t sci, bool active) { struct macsec_rx_sc *rx_sc; struct macsec_dev *macsec; struct net_device *real_dev = macsec_priv(dev)->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); struct macsec_secy *secy; list_for_each_entry(macsec, &rxd->secys, secys) { if (find_rx_sc_rtnl(&macsec->secy, sci)) return ERR_PTR(-EEXIST); } rx_sc = kzalloc(sizeof(*rx_sc), GFP_KERNEL); if (!rx_sc) return ERR_PTR(-ENOMEM); rx_sc->stats = netdev_alloc_pcpu_stats(struct pcpu_rx_sc_stats); if (!rx_sc->stats) { kfree(rx_sc); return ERR_PTR(-ENOMEM); } rx_sc->sci = sci; rx_sc->active = active; refcount_set(&rx_sc->refcnt, 1); secy = &macsec_priv(dev)->secy; rcu_assign_pointer(rx_sc->next, secy->rx_sc); rcu_assign_pointer(secy->rx_sc, rx_sc); if (rx_sc->active) secy->n_rx_sc++; return rx_sc; } static int init_tx_sa(struct macsec_tx_sa *tx_sa, char *sak, int key_len, int icv_len) { tx_sa->stats = alloc_percpu(struct macsec_tx_sa_stats); if (!tx_sa->stats) return -ENOMEM; tx_sa->key.tfm = macsec_alloc_tfm(sak, key_len, icv_len); if (IS_ERR(tx_sa->key.tfm)) { free_percpu(tx_sa->stats); return PTR_ERR(tx_sa->key.tfm); } tx_sa->ssci = MACSEC_UNDEF_SSCI; tx_sa->active = false; refcount_set(&tx_sa->refcnt, 1); spin_lock_init(&tx_sa->lock); return 0; } static void clear_tx_sa(struct macsec_tx_sa *tx_sa) { tx_sa->active = false; macsec_txsa_put(tx_sa); } static struct genl_family macsec_fam; static struct net_device *get_dev_from_nl(struct net *net, struct nlattr **attrs) { int ifindex = nla_get_u32(attrs[MACSEC_ATTR_IFINDEX]); struct net_device *dev; dev = __dev_get_by_index(net, ifindex); if (!dev) return ERR_PTR(-ENODEV); if (!netif_is_macsec(dev)) return ERR_PTR(-ENODEV); return dev; } static enum macsec_offload nla_get_offload(const struct nlattr *nla) { return (__force enum macsec_offload)nla_get_u8(nla); } static sci_t nla_get_sci(const struct nlattr *nla) { return (__force sci_t)nla_get_u64(nla); } static int nla_put_sci(struct sk_buff *skb, int attrtype, sci_t value, int padattr) { return nla_put_u64_64bit(skb, attrtype, (__force u64)value, padattr); } static ssci_t nla_get_ssci(const struct nlattr *nla) { return (__force ssci_t)nla_get_u32(nla); } static int nla_put_ssci(struct sk_buff *skb, int attrtype, ssci_t value) { return nla_put_u32(skb, attrtype, (__force u64)value); } static struct macsec_tx_sa *get_txsa_from_nl(struct net *net, struct nlattr **attrs, struct nlattr **tb_sa, struct net_device **devp, struct macsec_secy **secyp, struct macsec_tx_sc **scp, u8 *assoc_num) { struct net_device *dev; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; if (!tb_sa[MACSEC_SA_ATTR_AN]) return ERR_PTR(-EINVAL); *assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); dev = get_dev_from_nl(net, attrs); if (IS_ERR(dev)) return ERR_CAST(dev); if (*assoc_num >= MACSEC_NUM_AN) return ERR_PTR(-EINVAL); secy = &macsec_priv(dev)->secy; tx_sc = &secy->tx_sc; tx_sa = rtnl_dereference(tx_sc->sa[*assoc_num]); if (!tx_sa) return ERR_PTR(-ENODEV); *devp = dev; *scp = tx_sc; *secyp = secy; return tx_sa; } static struct macsec_rx_sc *get_rxsc_from_nl(struct net *net, struct nlattr **attrs, struct nlattr **tb_rxsc, struct net_device **devp, struct macsec_secy **secyp) { struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; sci_t sci; dev = get_dev_from_nl(net, attrs); if (IS_ERR(dev)) return ERR_CAST(dev); secy = &macsec_priv(dev)->secy; if (!tb_rxsc[MACSEC_RXSC_ATTR_SCI]) return ERR_PTR(-EINVAL); sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); rx_sc = find_rx_sc_rtnl(secy, sci); if (!rx_sc) return ERR_PTR(-ENODEV); *secyp = secy; *devp = dev; return rx_sc; } static struct macsec_rx_sa *get_rxsa_from_nl(struct net *net, struct nlattr **attrs, struct nlattr **tb_rxsc, struct nlattr **tb_sa, struct net_device **devp, struct macsec_secy **secyp, struct macsec_rx_sc **scp, u8 *assoc_num) { struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; if (!tb_sa[MACSEC_SA_ATTR_AN]) return ERR_PTR(-EINVAL); *assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); if (*assoc_num >= MACSEC_NUM_AN) return ERR_PTR(-EINVAL); rx_sc = get_rxsc_from_nl(net, attrs, tb_rxsc, devp, secyp); if (IS_ERR(rx_sc)) return ERR_CAST(rx_sc); rx_sa = rtnl_dereference(rx_sc->sa[*assoc_num]); if (!rx_sa) return ERR_PTR(-ENODEV); *scp = rx_sc; return rx_sa; } static const struct nla_policy macsec_genl_policy[NUM_MACSEC_ATTR] = { [MACSEC_ATTR_IFINDEX] = { .type = NLA_U32 }, [MACSEC_ATTR_RXSC_CONFIG] = { .type = NLA_NESTED }, [MACSEC_ATTR_SA_CONFIG] = { .type = NLA_NESTED }, [MACSEC_ATTR_OFFLOAD] = { .type = NLA_NESTED }, }; static const struct nla_policy macsec_genl_rxsc_policy[NUM_MACSEC_RXSC_ATTR] = { [MACSEC_RXSC_ATTR_SCI] = { .type = NLA_U64 }, [MACSEC_RXSC_ATTR_ACTIVE] = { .type = NLA_U8 }, }; static const struct nla_policy macsec_genl_sa_policy[NUM_MACSEC_SA_ATTR] = { [MACSEC_SA_ATTR_AN] = { .type = NLA_U8 }, [MACSEC_SA_ATTR_ACTIVE] = { .type = NLA_U8 }, [MACSEC_SA_ATTR_PN] = NLA_POLICY_MIN_LEN(4), [MACSEC_SA_ATTR_KEYID] = { .type = NLA_BINARY, .len = MACSEC_KEYID_LEN, }, [MACSEC_SA_ATTR_KEY] = { .type = NLA_BINARY, .len = MACSEC_MAX_KEY_LEN, }, [MACSEC_SA_ATTR_SSCI] = { .type = NLA_U32 }, [MACSEC_SA_ATTR_SALT] = { .type = NLA_BINARY, .len = MACSEC_SALT_LEN, }, }; static const struct nla_policy macsec_genl_offload_policy[NUM_MACSEC_OFFLOAD_ATTR] = { [MACSEC_OFFLOAD_ATTR_TYPE] = { .type = NLA_U8 }, }; /* Offloads an operation to a device driver */ static int macsec_offload(int (* const func)(struct macsec_context *), struct macsec_context *ctx) { int ret; if (unlikely(!func)) return 0; if (ctx->offload == MACSEC_OFFLOAD_PHY) mutex_lock(&ctx->phydev->lock); ret = (*func)(ctx); if (ctx->offload == MACSEC_OFFLOAD_PHY) mutex_unlock(&ctx->phydev->lock); return ret; } static int parse_sa_config(struct nlattr **attrs, struct nlattr **tb_sa) { if (!attrs[MACSEC_ATTR_SA_CONFIG]) return -EINVAL; if (nla_parse_nested_deprecated(tb_sa, MACSEC_SA_ATTR_MAX, attrs[MACSEC_ATTR_SA_CONFIG], macsec_genl_sa_policy, NULL)) return -EINVAL; return 0; } static int parse_rxsc_config(struct nlattr **attrs, struct nlattr **tb_rxsc) { if (!attrs[MACSEC_ATTR_RXSC_CONFIG]) return -EINVAL; if (nla_parse_nested_deprecated(tb_rxsc, MACSEC_RXSC_ATTR_MAX, attrs[MACSEC_ATTR_RXSC_CONFIG], macsec_genl_rxsc_policy, NULL)) return -EINVAL; return 0; } static bool validate_add_rxsa(struct nlattr **attrs) { if (!attrs[MACSEC_SA_ATTR_AN] || !attrs[MACSEC_SA_ATTR_KEY] || !attrs[MACSEC_SA_ATTR_KEYID]) return false; if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN) return false; if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0) return false; if (attrs[MACSEC_SA_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_SA_ATTR_ACTIVE]) > 1) return false; } if (nla_len(attrs[MACSEC_SA_ATTR_KEYID]) != MACSEC_KEYID_LEN) return false; return true; } static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; struct nlattr **attrs = info->attrs; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; unsigned char assoc_num; int pn_len; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; int err; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!validate_add_rxsa(tb_sa)) return -EINVAL; rtnl_lock(); rx_sc = get_rxsc_from_nl(genl_info_net(info), attrs, tb_rxsc, &dev, &secy); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); if (nla_len(tb_sa[MACSEC_SA_ATTR_KEY]) != secy->key_len) { pr_notice("macsec: nl: add_rxsa: bad key length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); rtnl_unlock(); return -EINVAL; } pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (tb_sa[MACSEC_SA_ATTR_PN] && nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: add_rxsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } if (secy->xpn) { if (!tb_sa[MACSEC_SA_ATTR_SSCI] || !tb_sa[MACSEC_SA_ATTR_SALT]) { rtnl_unlock(); return -EINVAL; } if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) { pr_notice("macsec: nl: add_rxsa: bad salt length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_SALT]), MACSEC_SALT_LEN); rtnl_unlock(); return -EINVAL; } } rx_sa = rtnl_dereference(rx_sc->sa[assoc_num]); if (rx_sa) { rtnl_unlock(); return -EBUSY; } rx_sa = kmalloc(sizeof(*rx_sa), GFP_KERNEL); if (!rx_sa) { rtnl_unlock(); return -ENOMEM; } err = init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len); if (err < 0) { kfree(rx_sa); rtnl_unlock(); return err; } if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&rx_sa->lock); rx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&rx_sa->lock); } if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) rx_sa->active = !!nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); rx_sa->sc = rx_sc; if (secy->xpn) { rx_sa->ssci = nla_get_ssci(tb_sa[MACSEC_SA_ATTR_SSCI]); nla_memcpy(rx_sa->key.salt.bytes, tb_sa[MACSEC_SA_ATTR_SALT], MACSEC_SALT_LEN); } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { err = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.rx_sa = rx_sa; ctx.secy = secy; memcpy(ctx.sa.key, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); err = macsec_offload(ops->mdo_add_rxsa, &ctx); memzero_explicit(ctx.sa.key, secy->key_len); if (err) goto cleanup; } nla_memcpy(rx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN); rcu_assign_pointer(rx_sc->sa[assoc_num], rx_sa); rtnl_unlock(); return 0; cleanup: macsec_rxsa_put(rx_sa); rtnl_unlock(); return err; } static bool validate_add_rxsc(struct nlattr **attrs) { if (!attrs[MACSEC_RXSC_ATTR_SCI]) return false; if (attrs[MACSEC_RXSC_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_RXSC_ATTR_ACTIVE]) > 1) return false; } return true; } static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; sci_t sci = MACSEC_UNDEF_SCI; struct nlattr **attrs = info->attrs; struct macsec_rx_sc *rx_sc; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct macsec_secy *secy; bool active = true; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!validate_add_rxsc(tb_rxsc)) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), attrs); if (IS_ERR(dev)) { rtnl_unlock(); return PTR_ERR(dev); } secy = &macsec_priv(dev)->secy; sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) active = nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]); rx_sc = create_rx_sc(dev, sci, active); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.rx_sc = rx_sc; ctx.secy = secy; ret = macsec_offload(ops->mdo_add_rxsc, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: del_rx_sc(secy, sci); free_rx_sc(rx_sc); rtnl_unlock(); return ret; } static bool validate_add_txsa(struct nlattr **attrs) { if (!attrs[MACSEC_SA_ATTR_AN] || !attrs[MACSEC_SA_ATTR_PN] || !attrs[MACSEC_SA_ATTR_KEY] || !attrs[MACSEC_SA_ATTR_KEYID]) return false; if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN) return false; if (nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0) return false; if (attrs[MACSEC_SA_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_SA_ATTR_ACTIVE]) > 1) return false; } if (nla_len(attrs[MACSEC_SA_ATTR_KEYID]) != MACSEC_KEYID_LEN) return false; return true; } static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; struct nlattr **attrs = info->attrs; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; unsigned char assoc_num; int pn_len; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; bool was_operational; int err; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (!validate_add_txsa(tb_sa)) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), attrs); if (IS_ERR(dev)) { rtnl_unlock(); return PTR_ERR(dev); } secy = &macsec_priv(dev)->secy; tx_sc = &secy->tx_sc; assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); if (nla_len(tb_sa[MACSEC_SA_ATTR_KEY]) != secy->key_len) { pr_notice("macsec: nl: add_txsa: bad key length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); rtnl_unlock(); return -EINVAL; } pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: add_txsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } if (secy->xpn) { if (!tb_sa[MACSEC_SA_ATTR_SSCI] || !tb_sa[MACSEC_SA_ATTR_SALT]) { rtnl_unlock(); return -EINVAL; } if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) { pr_notice("macsec: nl: add_txsa: bad salt length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_SALT]), MACSEC_SALT_LEN); rtnl_unlock(); return -EINVAL; } } tx_sa = rtnl_dereference(tx_sc->sa[assoc_num]); if (tx_sa) { rtnl_unlock(); return -EBUSY; } tx_sa = kmalloc(sizeof(*tx_sa), GFP_KERNEL); if (!tx_sa) { rtnl_unlock(); return -ENOMEM; } err = init_tx_sa(tx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len); if (err < 0) { kfree(tx_sa); rtnl_unlock(); return err; } spin_lock_bh(&tx_sa->lock); tx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&tx_sa->lock); if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) tx_sa->active = !!nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); was_operational = secy->operational; if (assoc_num == tx_sc->encoding_sa && tx_sa->active) secy->operational = true; if (secy->xpn) { tx_sa->ssci = nla_get_ssci(tb_sa[MACSEC_SA_ATTR_SSCI]); nla_memcpy(tx_sa->key.salt.bytes, tb_sa[MACSEC_SA_ATTR_SALT], MACSEC_SALT_LEN); } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { err = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.tx_sa = tx_sa; ctx.secy = secy; memcpy(ctx.sa.key, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); err = macsec_offload(ops->mdo_add_txsa, &ctx); memzero_explicit(ctx.sa.key, secy->key_len); if (err) goto cleanup; } nla_memcpy(tx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN); rcu_assign_pointer(tx_sc->sa[assoc_num], tx_sa); rtnl_unlock(); return 0; cleanup: secy->operational = was_operational; macsec_txsa_put(tx_sa); rtnl_unlock(); return err; } static int macsec_del_rxsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; u8 assoc_num; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; rtnl_lock(); rx_sa = get_rxsa_from_nl(genl_info_net(info), attrs, tb_rxsc, tb_sa, &dev, &secy, &rx_sc, &assoc_num); if (IS_ERR(rx_sa)) { rtnl_unlock(); return PTR_ERR(rx_sa); } if (rx_sa->active) { rtnl_unlock(); return -EBUSY; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.rx_sa = rx_sa; ctx.secy = secy; ret = macsec_offload(ops->mdo_del_rxsa, &ctx); if (ret) goto cleanup; } RCU_INIT_POINTER(rx_sc->sa[assoc_num], NULL); clear_rx_sa(rx_sa); rtnl_unlock(); return 0; cleanup: rtnl_unlock(); return ret; } static int macsec_del_rxsc(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; sci_t sci; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!tb_rxsc[MACSEC_RXSC_ATTR_SCI]) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), info->attrs); if (IS_ERR(dev)) { rtnl_unlock(); return PTR_ERR(dev); } secy = &macsec_priv(dev)->secy; sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); rx_sc = del_rx_sc(secy, sci); if (!rx_sc) { rtnl_unlock(); return -ENODEV; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.rx_sc = rx_sc; ctx.secy = secy; ret = macsec_offload(ops->mdo_del_rxsc, &ctx); if (ret) goto cleanup; } free_rx_sc(rx_sc); rtnl_unlock(); return 0; cleanup: rtnl_unlock(); return ret; } static int macsec_del_txsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; u8 assoc_num; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; rtnl_lock(); tx_sa = get_txsa_from_nl(genl_info_net(info), attrs, tb_sa, &dev, &secy, &tx_sc, &assoc_num); if (IS_ERR(tx_sa)) { rtnl_unlock(); return PTR_ERR(tx_sa); } if (tx_sa->active) { rtnl_unlock(); return -EBUSY; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.tx_sa = tx_sa; ctx.secy = secy; ret = macsec_offload(ops->mdo_del_txsa, &ctx); if (ret) goto cleanup; } RCU_INIT_POINTER(tx_sc->sa[assoc_num], NULL); clear_tx_sa(tx_sa); rtnl_unlock(); return 0; cleanup: rtnl_unlock(); return ret; } static bool validate_upd_sa(struct nlattr **attrs) { if (!attrs[MACSEC_SA_ATTR_AN] || attrs[MACSEC_SA_ATTR_KEY] || attrs[MACSEC_SA_ATTR_KEYID] || attrs[MACSEC_SA_ATTR_SSCI] || attrs[MACSEC_SA_ATTR_SALT]) return false; if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN) return false; if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0) return false; if (attrs[MACSEC_SA_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_SA_ATTR_ACTIVE]) > 1) return false; } return true; } static int macsec_upd_txsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; u8 assoc_num; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; bool was_operational, was_active; pn_t prev_pn; int ret = 0; prev_pn.full64 = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (!validate_upd_sa(tb_sa)) return -EINVAL; rtnl_lock(); tx_sa = get_txsa_from_nl(genl_info_net(info), attrs, tb_sa, &dev, &secy, &tx_sc, &assoc_num); if (IS_ERR(tx_sa)) { rtnl_unlock(); return PTR_ERR(tx_sa); } if (tb_sa[MACSEC_SA_ATTR_PN]) { int pn_len; pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: upd_txsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } spin_lock_bh(&tx_sa->lock); prev_pn = tx_sa->next_pn_halves; tx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&tx_sa->lock); } was_active = tx_sa->active; if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) tx_sa->active = nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); was_operational = secy->operational; if (assoc_num == tx_sc->encoding_sa) secy->operational = tx_sa->active; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.tx_sa = tx_sa; ctx.sa.update_pn = !!prev_pn.full64; ctx.secy = secy; ret = macsec_offload(ops->mdo_upd_txsa, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&tx_sa->lock); tx_sa->next_pn_halves = prev_pn; spin_unlock_bh(&tx_sa->lock); } tx_sa->active = was_active; secy->operational = was_operational; rtnl_unlock(); return ret; } static int macsec_upd_rxsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; u8 assoc_num; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; bool was_active; pn_t prev_pn; int ret = 0; prev_pn.full64 = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (!validate_upd_sa(tb_sa)) return -EINVAL; rtnl_lock(); rx_sa = get_rxsa_from_nl(genl_info_net(info), attrs, tb_rxsc, tb_sa, &dev, &secy, &rx_sc, &assoc_num); if (IS_ERR(rx_sa)) { rtnl_unlock(); return PTR_ERR(rx_sa); } if (tb_sa[MACSEC_SA_ATTR_PN]) { int pn_len; pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: upd_rxsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } spin_lock_bh(&rx_sa->lock); prev_pn = rx_sa->next_pn_halves; rx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&rx_sa->lock); } was_active = rx_sa->active; if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) rx_sa->active = nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.rx_sa = rx_sa; ctx.sa.update_pn = !!prev_pn.full64; ctx.secy = secy; ret = macsec_offload(ops->mdo_upd_rxsa, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&rx_sa->lock); rx_sa->next_pn_halves = prev_pn; spin_unlock_bh(&rx_sa->lock); } rx_sa->active = was_active; rtnl_unlock(); return ret; } static int macsec_upd_rxsc(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; unsigned int prev_n_rx_sc; bool was_active; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!validate_add_rxsc(tb_rxsc)) return -EINVAL; rtnl_lock(); rx_sc = get_rxsc_from_nl(genl_info_net(info), attrs, tb_rxsc, &dev, &secy); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } was_active = rx_sc->active; prev_n_rx_sc = secy->n_rx_sc; if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) { bool new = !!nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]); if (rx_sc->active != new) secy->n_rx_sc += new ? 1 : -1; rx_sc->active = new; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.rx_sc = rx_sc; ctx.secy = secy; ret = macsec_offload(ops->mdo_upd_rxsc, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: secy->n_rx_sc = prev_n_rx_sc; rx_sc->active = was_active; rtnl_unlock(); return ret; } static bool macsec_is_configured(struct macsec_dev *macsec) { struct macsec_secy *secy = &macsec->secy; struct macsec_tx_sc *tx_sc = &secy->tx_sc; int i; if (secy->rx_sc) return true; for (i = 0; i < MACSEC_NUM_AN; i++) if (tx_sc->sa[i]) return true; return false; } static bool macsec_needs_tx_tag(struct macsec_dev *macsec, const struct macsec_ops *ops) { return macsec->offload == MACSEC_OFFLOAD_PHY && ops->mdo_insert_tx_tag; } static void macsec_set_head_tail_room(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; int needed_headroom, needed_tailroom; const struct macsec_ops *ops; ops = macsec_get_ops(macsec, NULL); if (ops) { needed_headroom = ops->needed_headroom; needed_tailroom = ops->needed_tailroom; } else { needed_headroom = MACSEC_NEEDED_HEADROOM; needed_tailroom = MACSEC_NEEDED_TAILROOM; } dev->needed_headroom = real_dev->needed_headroom + needed_headroom; dev->needed_tailroom = real_dev->needed_tailroom + needed_tailroom; } static int macsec_update_offload(struct net_device *dev, enum macsec_offload offload) { enum macsec_offload prev_offload; const struct macsec_ops *ops; struct macsec_context ctx; struct macsec_dev *macsec; int ret = 0; macsec = macsec_priv(dev); /* Check if the offloading mode is supported by the underlying layers */ if (offload != MACSEC_OFFLOAD_OFF && !macsec_check_offload(offload, macsec)) return -EOPNOTSUPP; /* Check if the net device is busy. */ if (netif_running(dev)) return -EBUSY; /* Check if the device already has rules configured: we do not support * rules migration. */ if (macsec_is_configured(macsec)) return -EBUSY; prev_offload = macsec->offload; ops = __macsec_get_ops(offload == MACSEC_OFFLOAD_OFF ? prev_offload : offload, macsec, &ctx); if (!ops) return -EOPNOTSUPP; macsec->offload = offload; ctx.secy = &macsec->secy; ret = offload == MACSEC_OFFLOAD_OFF ? macsec_offload(ops->mdo_del_secy, &ctx) : macsec_offload(ops->mdo_add_secy, &ctx); if (ret) { macsec->offload = prev_offload; return ret; } macsec_set_head_tail_room(dev); macsec->insert_tx_tag = macsec_needs_tx_tag(macsec, ops); return ret; } static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb_offload[MACSEC_OFFLOAD_ATTR_MAX + 1]; struct nlattr **attrs = info->attrs; enum macsec_offload offload; struct macsec_dev *macsec; struct net_device *dev; int ret = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (!attrs[MACSEC_ATTR_OFFLOAD]) return -EINVAL; if (nla_parse_nested_deprecated(tb_offload, MACSEC_OFFLOAD_ATTR_MAX, attrs[MACSEC_ATTR_OFFLOAD], macsec_genl_offload_policy, NULL)) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), attrs); if (IS_ERR(dev)) { ret = PTR_ERR(dev); goto out; } macsec = macsec_priv(dev); if (!tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]) { ret = -EINVAL; goto out; } offload = nla_get_u8(tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]); if (macsec->offload != offload) ret = macsec_update_offload(dev, offload); out: rtnl_unlock(); return ret; } static void get_tx_sa_stats(struct net_device *dev, int an, struct macsec_tx_sa *tx_sa, struct macsec_tx_sa_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.sa.assoc_num = an; ctx.sa.tx_sa = tx_sa; ctx.stats.tx_sa_stats = sum; ctx.secy = &macsec_priv(dev)->secy; macsec_offload(ops->mdo_get_tx_sa_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct macsec_tx_sa_stats *stats = per_cpu_ptr(tx_sa->stats, cpu); sum->OutPktsProtected += stats->OutPktsProtected; sum->OutPktsEncrypted += stats->OutPktsEncrypted; } } static int copy_tx_sa_stats(struct sk_buff *skb, struct macsec_tx_sa_stats *sum) { if (nla_put_u32(skb, MACSEC_SA_STATS_ATTR_OUT_PKTS_PROTECTED, sum->OutPktsProtected) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_OUT_PKTS_ENCRYPTED, sum->OutPktsEncrypted)) return -EMSGSIZE; return 0; } static void get_rx_sa_stats(struct net_device *dev, struct macsec_rx_sc *rx_sc, int an, struct macsec_rx_sa *rx_sa, struct macsec_rx_sa_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.sa.assoc_num = an; ctx.sa.rx_sa = rx_sa; ctx.stats.rx_sa_stats = sum; ctx.secy = &macsec_priv(dev)->secy; ctx.rx_sc = rx_sc; macsec_offload(ops->mdo_get_rx_sa_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct macsec_rx_sa_stats *stats = per_cpu_ptr(rx_sa->stats, cpu); sum->InPktsOK += stats->InPktsOK; sum->InPktsInvalid += stats->InPktsInvalid; sum->InPktsNotValid += stats->InPktsNotValid; sum->InPktsNotUsingSA += stats->InPktsNotUsingSA; sum->InPktsUnusedSA += stats->InPktsUnusedSA; } } static int copy_rx_sa_stats(struct sk_buff *skb, struct macsec_rx_sa_stats *sum) { if (nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_OK, sum->InPktsOK) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_INVALID, sum->InPktsInvalid) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_NOT_VALID, sum->InPktsNotValid) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_NOT_USING_SA, sum->InPktsNotUsingSA) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_UNUSED_SA, sum->InPktsUnusedSA)) return -EMSGSIZE; return 0; } static void get_rx_sc_stats(struct net_device *dev, struct macsec_rx_sc *rx_sc, struct macsec_rx_sc_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.stats.rx_sc_stats = sum; ctx.secy = &macsec_priv(dev)->secy; ctx.rx_sc = rx_sc; macsec_offload(ops->mdo_get_rx_sc_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct pcpu_rx_sc_stats *stats; struct macsec_rx_sc_stats tmp; unsigned int start; stats = per_cpu_ptr(rx_sc->stats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); memcpy(&tmp, &stats->stats, sizeof(tmp)); } while (u64_stats_fetch_retry(&stats->syncp, start)); sum->InOctetsValidated += tmp.InOctetsValidated; sum->InOctetsDecrypted += tmp.InOctetsDecrypted; sum->InPktsUnchecked += tmp.InPktsUnchecked; sum->InPktsDelayed += tmp.InPktsDelayed; sum->InPktsOK += tmp.InPktsOK; sum->InPktsInvalid += tmp.InPktsInvalid; sum->InPktsLate += tmp.InPktsLate; sum->InPktsNotValid += tmp.InPktsNotValid; sum->InPktsNotUsingSA += tmp.InPktsNotUsingSA; sum->InPktsUnusedSA += tmp.InPktsUnusedSA; } } static int copy_rx_sc_stats(struct sk_buff *skb, struct macsec_rx_sc_stats *sum) { if (nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_OCTETS_VALIDATED, sum->InOctetsValidated, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_OCTETS_DECRYPTED, sum->InOctetsDecrypted, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_UNCHECKED, sum->InPktsUnchecked, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_DELAYED, sum->InPktsDelayed, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_OK, sum->InPktsOK, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_INVALID, sum->InPktsInvalid, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_LATE, sum->InPktsLate, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_NOT_VALID, sum->InPktsNotValid, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_NOT_USING_SA, sum->InPktsNotUsingSA, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_UNUSED_SA, sum->InPktsUnusedSA, MACSEC_RXSC_STATS_ATTR_PAD)) return -EMSGSIZE; return 0; } static void get_tx_sc_stats(struct net_device *dev, struct macsec_tx_sc_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.stats.tx_sc_stats = sum; ctx.secy = &macsec_priv(dev)->secy; macsec_offload(ops->mdo_get_tx_sc_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct pcpu_tx_sc_stats *stats; struct macsec_tx_sc_stats tmp; unsigned int start; stats = per_cpu_ptr(macsec_priv(dev)->secy.tx_sc.stats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); memcpy(&tmp, &stats->stats, sizeof(tmp)); } while (u64_stats_fetch_retry(&stats->syncp, start)); sum->OutPktsProtected += tmp.OutPktsProtected; sum->OutPktsEncrypted += tmp.OutPktsEncrypted; sum->OutOctetsProtected += tmp.OutOctetsProtected; sum->OutOctetsEncrypted += tmp.OutOctetsEncrypted; } } static int copy_tx_sc_stats(struct sk_buff *skb, struct macsec_tx_sc_stats *sum) { if (nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_PKTS_PROTECTED, sum->OutPktsProtected, MACSEC_TXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_PKTS_ENCRYPTED, sum->OutPktsEncrypted, MACSEC_TXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_OCTETS_PROTECTED, sum->OutOctetsProtected, MACSEC_TXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_OCTETS_ENCRYPTED, sum->OutOctetsEncrypted, MACSEC_TXSC_STATS_ATTR_PAD)) return -EMSGSIZE; return 0; } static void get_secy_stats(struct net_device *dev, struct macsec_dev_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.stats.dev_stats = sum; ctx.secy = &macsec_priv(dev)->secy; macsec_offload(ops->mdo_get_dev_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct pcpu_secy_stats *stats; struct macsec_dev_stats tmp; unsigned int start; stats = per_cpu_ptr(macsec_priv(dev)->stats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); memcpy(&tmp, &stats->stats, sizeof(tmp)); } while (u64_stats_fetch_retry(&stats->syncp, start)); sum->OutPktsUntagged += tmp.OutPktsUntagged; sum->InPktsUntagged += tmp.InPktsUntagged; sum->OutPktsTooLong += tmp.OutPktsTooLong; sum->InPktsNoTag += tmp.InPktsNoTag; sum->InPktsBadTag += tmp.InPktsBadTag; sum->InPktsUnknownSCI += tmp.InPktsUnknownSCI; sum->InPktsNoSCI += tmp.InPktsNoSCI; sum->InPktsOverrun += tmp.InPktsOverrun; } } static int copy_secy_stats(struct sk_buff *skb, struct macsec_dev_stats *sum) { if (nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_OUT_PKTS_UNTAGGED, sum->OutPktsUntagged, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_UNTAGGED, sum->InPktsUntagged, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_OUT_PKTS_TOO_LONG, sum->OutPktsTooLong, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_NO_TAG, sum->InPktsNoTag, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_BAD_TAG, sum->InPktsBadTag, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_UNKNOWN_SCI, sum->InPktsUnknownSCI, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_NO_SCI, sum->InPktsNoSCI, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_OVERRUN, sum->InPktsOverrun, MACSEC_SECY_STATS_ATTR_PAD)) return -EMSGSIZE; return 0; } static int nla_put_secy(struct macsec_secy *secy, struct sk_buff *skb) { struct macsec_tx_sc *tx_sc = &secy->tx_sc; struct nlattr *secy_nest = nla_nest_start_noflag(skb, MACSEC_ATTR_SECY); u64 csid; if (!secy_nest) return 1; switch (secy->key_len) { case MACSEC_GCM_AES_128_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_128 : MACSEC_DEFAULT_CIPHER_ID; break; case MACSEC_GCM_AES_256_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_256 : MACSEC_CIPHER_ID_GCM_AES_256; break; default: goto cancel; } if (nla_put_sci(skb, MACSEC_SECY_ATTR_SCI, secy->sci, MACSEC_SECY_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_ATTR_CIPHER_SUITE, csid, MACSEC_SECY_ATTR_PAD) || nla_put_u8(skb, MACSEC_SECY_ATTR_ICV_LEN, secy->icv_len) || nla_put_u8(skb, MACSEC_SECY_ATTR_OPER, secy->operational) || nla_put_u8(skb, MACSEC_SECY_ATTR_PROTECT, secy->protect_frames) || nla_put_u8(skb, MACSEC_SECY_ATTR_REPLAY, secy->replay_protect) || nla_put_u8(skb, MACSEC_SECY_ATTR_VALIDATE, secy->validate_frames) || nla_put_u8(skb, MACSEC_SECY_ATTR_ENCRYPT, tx_sc->encrypt) || nla_put_u8(skb, MACSEC_SECY_ATTR_INC_SCI, tx_sc->send_sci) || nla_put_u8(skb, MACSEC_SECY_ATTR_ES, tx_sc->end_station) || nla_put_u8(skb, MACSEC_SECY_ATTR_SCB, tx_sc->scb) || nla_put_u8(skb, MACSEC_SECY_ATTR_ENCODING_SA, tx_sc->encoding_sa)) goto cancel; if (secy->replay_protect) { if (nla_put_u32(skb, MACSEC_SECY_ATTR_WINDOW, secy->replay_window)) goto cancel; } nla_nest_end(skb, secy_nest); return 0; cancel: nla_nest_cancel(skb, secy_nest); return 1; } static noinline_for_stack int dump_secy(struct macsec_secy *secy, struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct macsec_tx_sc_stats tx_sc_stats = {0, }; struct macsec_tx_sa_stats tx_sa_stats = {0, }; struct macsec_rx_sc_stats rx_sc_stats = {0, }; struct macsec_rx_sa_stats rx_sa_stats = {0, }; struct macsec_dev *macsec = netdev_priv(dev); struct macsec_dev_stats dev_stats = {0, }; struct macsec_tx_sc *tx_sc = &secy->tx_sc; struct nlattr *txsa_list, *rxsc_list; struct macsec_rx_sc *rx_sc; struct nlattr *attr; void *hdr; int i, j; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &macsec_fam, NLM_F_MULTI, MACSEC_CMD_GET_TXSC); if (!hdr) return -EMSGSIZE; genl_dump_check_consistent(cb, hdr); if (nla_put_u32(skb, MACSEC_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; attr = nla_nest_start_noflag(skb, MACSEC_ATTR_OFFLOAD); if (!attr) goto nla_put_failure; if (nla_put_u8(skb, MACSEC_OFFLOAD_ATTR_TYPE, macsec->offload)) goto nla_put_failure; nla_nest_end(skb, attr); if (nla_put_secy(secy, skb)) goto nla_put_failure; attr = nla_nest_start_noflag(skb, MACSEC_ATTR_TXSC_STATS); if (!attr) goto nla_put_failure; get_tx_sc_stats(dev, &tx_sc_stats); if (copy_tx_sc_stats(skb, &tx_sc_stats)) { nla_nest_cancel(skb, attr); goto nla_put_failure; } nla_nest_end(skb, attr); attr = nla_nest_start_noflag(skb, MACSEC_ATTR_SECY_STATS); if (!attr) goto nla_put_failure; get_secy_stats(dev, &dev_stats); if (copy_secy_stats(skb, &dev_stats)) { nla_nest_cancel(skb, attr); goto nla_put_failure; } nla_nest_end(skb, attr); txsa_list = nla_nest_start_noflag(skb, MACSEC_ATTR_TXSA_LIST); if (!txsa_list) goto nla_put_failure; for (i = 0, j = 1; i < MACSEC_NUM_AN; i++) { struct macsec_tx_sa *tx_sa = rtnl_dereference(tx_sc->sa[i]); struct nlattr *txsa_nest; u64 pn; int pn_len; if (!tx_sa) continue; txsa_nest = nla_nest_start_noflag(skb, j++); if (!txsa_nest) { nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } attr = nla_nest_start_noflag(skb, MACSEC_SA_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } memset(&tx_sa_stats, 0, sizeof(tx_sa_stats)); get_tx_sa_stats(dev, i, tx_sa, &tx_sa_stats); if (copy_tx_sa_stats(skb, &tx_sa_stats)) { nla_nest_cancel(skb, attr); nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } nla_nest_end(skb, attr); if (secy->xpn) { pn = tx_sa->next_pn; pn_len = MACSEC_XPN_PN_LEN; } else { pn = tx_sa->next_pn_halves.lower; pn_len = MACSEC_DEFAULT_PN_LEN; } if (nla_put_u8(skb, MACSEC_SA_ATTR_AN, i) || nla_put(skb, MACSEC_SA_ATTR_PN, pn_len, &pn) || nla_put(skb, MACSEC_SA_ATTR_KEYID, MACSEC_KEYID_LEN, tx_sa->key.id) || (secy->xpn && nla_put_ssci(skb, MACSEC_SA_ATTR_SSCI, tx_sa->ssci)) || nla_put_u8(skb, MACSEC_SA_ATTR_ACTIVE, tx_sa->active)) { nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } nla_nest_end(skb, txsa_nest); } nla_nest_end(skb, txsa_list); rxsc_list = nla_nest_start_noflag(skb, MACSEC_ATTR_RXSC_LIST); if (!rxsc_list) goto nla_put_failure; j = 1; for_each_rxsc_rtnl(secy, rx_sc) { int k; struct nlattr *rxsa_list; struct nlattr *rxsc_nest = nla_nest_start_noflag(skb, j++); if (!rxsc_nest) { nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } if (nla_put_u8(skb, MACSEC_RXSC_ATTR_ACTIVE, rx_sc->active) || nla_put_sci(skb, MACSEC_RXSC_ATTR_SCI, rx_sc->sci, MACSEC_RXSC_ATTR_PAD)) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } attr = nla_nest_start_noflag(skb, MACSEC_RXSC_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } memset(&rx_sc_stats, 0, sizeof(rx_sc_stats)); get_rx_sc_stats(dev, rx_sc, &rx_sc_stats); if (copy_rx_sc_stats(skb, &rx_sc_stats)) { nla_nest_cancel(skb, attr); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } nla_nest_end(skb, attr); rxsa_list = nla_nest_start_noflag(skb, MACSEC_RXSC_ATTR_SA_LIST); if (!rxsa_list) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } for (i = 0, k = 1; i < MACSEC_NUM_AN; i++) { struct macsec_rx_sa *rx_sa = rtnl_dereference(rx_sc->sa[i]); struct nlattr *rxsa_nest; u64 pn; int pn_len; if (!rx_sa) continue; rxsa_nest = nla_nest_start_noflag(skb, k++); if (!rxsa_nest) { nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } attr = nla_nest_start_noflag(skb, MACSEC_SA_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } memset(&rx_sa_stats, 0, sizeof(rx_sa_stats)); get_rx_sa_stats(dev, rx_sc, i, rx_sa, &rx_sa_stats); if (copy_rx_sa_stats(skb, &rx_sa_stats)) { nla_nest_cancel(skb, attr); nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } nla_nest_end(skb, attr); if (secy->xpn) { pn = rx_sa->next_pn; pn_len = MACSEC_XPN_PN_LEN; } else { pn = rx_sa->next_pn_halves.lower; pn_len = MACSEC_DEFAULT_PN_LEN; } if (nla_put_u8(skb, MACSEC_SA_ATTR_AN, i) || nla_put(skb, MACSEC_SA_ATTR_PN, pn_len, &pn) || nla_put(skb, MACSEC_SA_ATTR_KEYID, MACSEC_KEYID_LEN, rx_sa->key.id) || (secy->xpn && nla_put_ssci(skb, MACSEC_SA_ATTR_SSCI, rx_sa->ssci)) || nla_put_u8(skb, MACSEC_SA_ATTR_ACTIVE, rx_sa->active)) { nla_nest_cancel(skb, rxsa_nest); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } nla_nest_end(skb, rxsa_nest); } nla_nest_end(skb, rxsa_list); nla_nest_end(skb, rxsc_nest); } nla_nest_end(skb, rxsc_list); genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int macsec_generation = 1; /* protected by RTNL */ static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct net_device *dev; int dev_idx, d; dev_idx = cb->args[0]; d = 0; rtnl_lock(); cb->seq = macsec_generation; for_each_netdev(net, dev) { struct macsec_secy *secy; if (d < dev_idx) goto next; if (!netif_is_macsec(dev)) goto next; secy = &macsec_priv(dev)->secy; if (dump_secy(secy, dev, skb, cb) < 0) goto done; next: d++; } done: rtnl_unlock(); cb->args[0] = d; return skb->len; } static const struct genl_small_ops macsec_genl_ops[] = { { .cmd = MACSEC_CMD_GET_TXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = macsec_dump_txsc, }, { .cmd = MACSEC_CMD_ADD_RXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_add_rxsc, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_RXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_del_rxsc, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_RXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_rxsc, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_ADD_TXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_add_txsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_TXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_del_txsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_TXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_txsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_ADD_RXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_add_rxsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_RXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_del_rxsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_RXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_rxsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_OFFLOAD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_offload, .flags = GENL_ADMIN_PERM, }, }; static struct genl_family macsec_fam __ro_after_init = { .name = MACSEC_GENL_NAME, .hdrsize = 0, .version = MACSEC_GENL_VERSION, .maxattr = MACSEC_ATTR_MAX, .policy = macsec_genl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = macsec_genl_ops, .n_small_ops = ARRAY_SIZE(macsec_genl_ops), .resv_start_op = MACSEC_CMD_UPD_OFFLOAD + 1, }; static struct sk_buff *macsec_insert_tx_tag(struct sk_buff *skb, struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); const struct macsec_ops *ops; struct phy_device *phydev; struct macsec_context ctx; int skb_final_len; int err; ops = macsec_get_ops(macsec, &ctx); skb_final_len = skb->len - ETH_HLEN + ops->needed_headroom + ops->needed_tailroom; if (unlikely(skb_final_len > macsec->real_dev->mtu)) { err = -EINVAL; goto cleanup; } phydev = macsec->real_dev->phydev; err = skb_ensure_writable_head_tail(skb, dev); if (unlikely(err < 0)) goto cleanup; err = ops->mdo_insert_tx_tag(phydev, skb); if (unlikely(err)) goto cleanup; return skb; cleanup: kfree_skb(skb); return ERR_PTR(err); } static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct macsec_dev *macsec = netdev_priv(dev); struct macsec_secy *secy = &macsec->secy; struct pcpu_secy_stats *secy_stats; int ret, len; if (macsec_is_offloaded(netdev_priv(dev))) { struct metadata_dst *md_dst = secy->tx_sc.md_dst; skb_dst_drop(skb); dst_hold(&md_dst->dst); skb_dst_set(skb, &md_dst->dst); if (macsec->insert_tx_tag) { skb = macsec_insert_tx_tag(skb, dev); if (IS_ERR(skb)) { DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } } skb->dev = macsec->real_dev; return dev_queue_xmit(skb); } /* 10.5 */ if (!secy->protect_frames) { secy_stats = this_cpu_ptr(macsec->stats); u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.OutPktsUntagged++; u64_stats_update_end(&secy_stats->syncp); skb->dev = macsec->real_dev; len = skb->len; ret = dev_queue_xmit(skb); count_tx(dev, ret, len); return ret; } if (!secy->operational) { kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } len = skb->len; skb = macsec_encrypt(skb, dev); if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EINPROGRESS) DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } macsec_count_tx(skb, &macsec->secy.tx_sc, macsec_skb_cb(skb)->tx_sa); macsec_encrypt_finish(skb, dev); ret = dev_queue_xmit(skb); count_tx(dev, ret, len); return ret; } #define MACSEC_FEATURES \ (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) static int macsec_dev_init(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; int err; err = gro_cells_init(&macsec->gro_cells, dev); if (err) return err; dev->features = real_dev->features & MACSEC_FEATURES; dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; macsec_set_head_tail_room(dev); if (is_zero_ether_addr(dev->dev_addr)) eth_hw_addr_inherit(dev, real_dev); if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len); /* Get macsec's reference to real_dev */ netdev_hold(real_dev, &macsec->dev_tracker, GFP_KERNEL); return 0; } static void macsec_dev_uninit(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); gro_cells_destroy(&macsec->gro_cells); } static netdev_features_t macsec_fix_features(struct net_device *dev, netdev_features_t features) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; features &= (real_dev->features & MACSEC_FEATURES) | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES; features |= NETIF_F_LLTX; return features; } static int macsec_dev_open(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; int err; err = dev_uc_add(real_dev, dev->dev_addr); if (err < 0) return err; if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(real_dev, 1); if (err < 0) goto del_unicast; } if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(real_dev, 1); if (err < 0) goto clear_allmulti; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { err = -EOPNOTSUPP; goto clear_allmulti; } ctx.secy = &macsec->secy; err = macsec_offload(ops->mdo_dev_open, &ctx); if (err) goto clear_allmulti; } if (netif_carrier_ok(real_dev)) netif_carrier_on(dev); return 0; clear_allmulti: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(real_dev, -1); del_unicast: dev_uc_del(real_dev, dev->dev_addr); netif_carrier_off(dev); return err; } static int macsec_dev_stop(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; netif_carrier_off(dev); /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.secy = &macsec->secy; macsec_offload(ops->mdo_dev_stop, &ctx); } } dev_mc_unsync(real_dev, dev); dev_uc_unsync(real_dev, dev); if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(real_dev, -1); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(real_dev, -1); dev_uc_del(real_dev, dev->dev_addr); return 0; } static void macsec_dev_change_rx_flags(struct net_device *dev, int change) { struct net_device *real_dev = macsec_priv(dev)->real_dev; if (!(dev->flags & IFF_UP)) return; if (change & IFF_ALLMULTI) dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1); } static void macsec_dev_set_rx_mode(struct net_device *dev) { struct net_device *real_dev = macsec_priv(dev)->real_dev; dev_mc_sync(real_dev, dev); dev_uc_sync(real_dev, dev); } static int macsec_set_mac_address(struct net_device *dev, void *p) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; struct sockaddr *addr = p; u8 old_addr[ETH_ALEN]; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; if (dev->flags & IFF_UP) { err = dev_uc_add(real_dev, addr->sa_data); if (err < 0) return err; } ether_addr_copy(old_addr, dev->dev_addr); eth_hw_addr_set(dev, addr->sa_data); /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (!ops) { err = -EOPNOTSUPP; goto restore_old_addr; } ctx.secy = &macsec->secy; err = macsec_offload(ops->mdo_upd_secy, &ctx); if (err) goto restore_old_addr; } if (dev->flags & IFF_UP) dev_uc_del(real_dev, old_addr); return 0; restore_old_addr: if (dev->flags & IFF_UP) dev_uc_del(real_dev, addr->sa_data); eth_hw_addr_set(dev, old_addr); return err; } static int macsec_change_mtu(struct net_device *dev, int new_mtu) { struct macsec_dev *macsec = macsec_priv(dev); unsigned int extra = macsec->secy.icv_len + macsec_extra_len(true); if (macsec->real_dev->mtu - extra < new_mtu) return -ERANGE; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static void macsec_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { if (!dev->tstats) return; dev_fetch_sw_netstats(s, dev->tstats); s->rx_dropped = DEV_STATS_READ(dev, rx_dropped); s->tx_dropped = DEV_STATS_READ(dev, tx_dropped); s->rx_errors = DEV_STATS_READ(dev, rx_errors); } static int macsec_get_iflink(const struct net_device *dev) { return READ_ONCE(macsec_priv(dev)->real_dev->ifindex); } static const struct net_device_ops macsec_netdev_ops = { .ndo_init = macsec_dev_init, .ndo_uninit = macsec_dev_uninit, .ndo_open = macsec_dev_open, .ndo_stop = macsec_dev_stop, .ndo_fix_features = macsec_fix_features, .ndo_change_mtu = macsec_change_mtu, .ndo_set_rx_mode = macsec_dev_set_rx_mode, .ndo_change_rx_flags = macsec_dev_change_rx_flags, .ndo_set_mac_address = macsec_set_mac_address, .ndo_start_xmit = macsec_start_xmit, .ndo_get_stats64 = macsec_get_stats64, .ndo_get_iflink = macsec_get_iflink, }; static const struct device_type macsec_type = { .name = "macsec", }; static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = { [IFLA_MACSEC_SCI] = { .type = NLA_U64 }, [IFLA_MACSEC_PORT] = { .type = NLA_U16 }, [IFLA_MACSEC_ICV_LEN] = { .type = NLA_U8 }, [IFLA_MACSEC_CIPHER_SUITE] = { .type = NLA_U64 }, [IFLA_MACSEC_WINDOW] = { .type = NLA_U32 }, [IFLA_MACSEC_ENCODING_SA] = { .type = NLA_U8 }, [IFLA_MACSEC_ENCRYPT] = { .type = NLA_U8 }, [IFLA_MACSEC_PROTECT] = { .type = NLA_U8 }, [IFLA_MACSEC_INC_SCI] = { .type = NLA_U8 }, [IFLA_MACSEC_ES] = { .type = NLA_U8 }, [IFLA_MACSEC_SCB] = { .type = NLA_U8 }, [IFLA_MACSEC_REPLAY_PROTECT] = { .type = NLA_U8 }, [IFLA_MACSEC_VALIDATION] = { .type = NLA_U8 }, [IFLA_MACSEC_OFFLOAD] = { .type = NLA_U8 }, }; static void macsec_free_netdev(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); if (macsec->secy.tx_sc.md_dst) metadata_dst_free(macsec->secy.tx_sc.md_dst); free_percpu(macsec->stats); free_percpu(macsec->secy.tx_sc.stats); /* Get rid of the macsec's reference to real_dev */ netdev_put(macsec->real_dev, &macsec->dev_tracker); } static void macsec_setup(struct net_device *dev) { ether_setup(dev); dev->min_mtu = 0; dev->max_mtu = ETH_MAX_MTU; dev->priv_flags |= IFF_NO_QUEUE; dev->netdev_ops = &macsec_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = macsec_free_netdev; SET_NETDEV_DEVTYPE(dev, &macsec_type); eth_zero_addr(dev->broadcast); } static int macsec_changelink_common(struct net_device *dev, struct nlattr *data[]) { struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; secy = &macsec_priv(dev)->secy; tx_sc = &secy->tx_sc; if (data[IFLA_MACSEC_ENCODING_SA]) { struct macsec_tx_sa *tx_sa; tx_sc->encoding_sa = nla_get_u8(data[IFLA_MACSEC_ENCODING_SA]); tx_sa = rtnl_dereference(tx_sc->sa[tx_sc->encoding_sa]); secy->operational = tx_sa && tx_sa->active; } if (data[IFLA_MACSEC_ENCRYPT]) tx_sc->encrypt = !!nla_get_u8(data[IFLA_MACSEC_ENCRYPT]); if (data[IFLA_MACSEC_PROTECT]) secy->protect_frames = !!nla_get_u8(data[IFLA_MACSEC_PROTECT]); if (data[IFLA_MACSEC_INC_SCI]) tx_sc->send_sci = !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]); if (data[IFLA_MACSEC_ES]) tx_sc->end_station = !!nla_get_u8(data[IFLA_MACSEC_ES]); if (data[IFLA_MACSEC_SCB]) tx_sc->scb = !!nla_get_u8(data[IFLA_MACSEC_SCB]); if (data[IFLA_MACSEC_REPLAY_PROTECT]) secy->replay_protect = !!nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT]); if (data[IFLA_MACSEC_VALIDATION]) secy->validate_frames = nla_get_u8(data[IFLA_MACSEC_VALIDATION]); if (data[IFLA_MACSEC_CIPHER_SUITE]) { switch (nla_get_u64(data[IFLA_MACSEC_CIPHER_SUITE])) { case MACSEC_CIPHER_ID_GCM_AES_128: case MACSEC_DEFAULT_CIPHER_ID: secy->key_len = MACSEC_GCM_AES_128_SAK_LEN; secy->xpn = false; break; case MACSEC_CIPHER_ID_GCM_AES_256: secy->key_len = MACSEC_GCM_AES_256_SAK_LEN; secy->xpn = false; break; case MACSEC_CIPHER_ID_GCM_AES_XPN_128: secy->key_len = MACSEC_GCM_AES_128_SAK_LEN; secy->xpn = true; break; case MACSEC_CIPHER_ID_GCM_AES_XPN_256: secy->key_len = MACSEC_GCM_AES_256_SAK_LEN; secy->xpn = true; break; default: return -EINVAL; } } if (data[IFLA_MACSEC_WINDOW]) { secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]); /* IEEE 802.1AEbw-2013 10.7.8 - maximum replay window * for XPN cipher suites */ if (secy->xpn && secy->replay_window > MACSEC_XPN_MAX_REPLAY_WINDOW) return -EINVAL; } return 0; } static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macsec_dev *macsec = macsec_priv(dev); bool macsec_offload_state_change = false; enum macsec_offload offload; struct macsec_tx_sc tx_sc; struct macsec_secy secy; int ret; if (!data) return 0; if (data[IFLA_MACSEC_CIPHER_SUITE] || data[IFLA_MACSEC_ICV_LEN] || data[IFLA_MACSEC_SCI] || data[IFLA_MACSEC_PORT]) return -EINVAL; /* Keep a copy of unmodified secy and tx_sc, in case the offload * propagation fails, to revert macsec_changelink_common. */ memcpy(&secy, &macsec->secy, sizeof(secy)); memcpy(&tx_sc, &macsec->secy.tx_sc, sizeof(tx_sc)); ret = macsec_changelink_common(dev, data); if (ret) goto cleanup; if (data[IFLA_MACSEC_OFFLOAD]) { offload = nla_get_u8(data[IFLA_MACSEC_OFFLOAD]); if (macsec->offload != offload) { macsec_offload_state_change = true; ret = macsec_update_offload(dev, offload); if (ret) goto cleanup; } } /* If h/w offloading is available, propagate to the device */ if (!macsec_offload_state_change && macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.secy = &macsec->secy; ret = macsec_offload(ops->mdo_upd_secy, &ctx); if (ret) goto cleanup; } return 0; cleanup: memcpy(&macsec->secy.tx_sc, &tx_sc, sizeof(tx_sc)); memcpy(&macsec->secy, &secy, sizeof(secy)); return ret; } static void macsec_del_dev(struct macsec_dev *macsec) { int i; while (macsec->secy.rx_sc) { struct macsec_rx_sc *rx_sc = rtnl_dereference(macsec->secy.rx_sc); rcu_assign_pointer(macsec->secy.rx_sc, rx_sc->next); free_rx_sc(rx_sc); } for (i = 0; i < MACSEC_NUM_AN; i++) { struct macsec_tx_sa *sa = rtnl_dereference(macsec->secy.tx_sc.sa[i]); if (sa) { RCU_INIT_POINTER(macsec->secy.tx_sc.sa[i], NULL); clear_tx_sa(sa); } } } static void macsec_common_dellink(struct net_device *dev, struct list_head *head) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (ops) { ctx.secy = &macsec->secy; macsec_offload(ops->mdo_del_secy, &ctx); } } unregister_netdevice_queue(dev, head); list_del_rcu(&macsec->secys); macsec_del_dev(macsec); netdev_upper_dev_unlink(real_dev, dev); macsec_generation++; } static void macsec_dellink(struct net_device *dev, struct list_head *head) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); macsec_common_dellink(dev, head); if (list_empty(&rxd->secys)) { netdev_rx_handler_unregister(real_dev); kfree(rxd); } } static int register_macsec_dev(struct net_device *real_dev, struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); if (!rxd) { int err; rxd = kmalloc(sizeof(*rxd), GFP_KERNEL); if (!rxd) return -ENOMEM; INIT_LIST_HEAD(&rxd->secys); err = netdev_rx_handler_register(real_dev, macsec_handle_frame, rxd); if (err < 0) { kfree(rxd); return err; } } list_add_tail_rcu(&macsec->secys, &rxd->secys); return 0; } static bool sci_exists(struct net_device *dev, sci_t sci) { struct macsec_rxh_data *rxd = macsec_data_rtnl(dev); struct macsec_dev *macsec; list_for_each_entry(macsec, &rxd->secys, secys) { if (macsec->secy.sci == sci) return true; } return false; } static sci_t dev_to_sci(struct net_device *dev, __be16 port) { return make_sci(dev->dev_addr, port); } static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len) { struct macsec_dev *macsec = macsec_priv(dev); struct macsec_secy *secy = &macsec->secy; macsec->stats = netdev_alloc_pcpu_stats(struct pcpu_secy_stats); if (!macsec->stats) return -ENOMEM; secy->tx_sc.stats = netdev_alloc_pcpu_stats(struct pcpu_tx_sc_stats); if (!secy->tx_sc.stats) return -ENOMEM; secy->tx_sc.md_dst = metadata_dst_alloc(0, METADATA_MACSEC, GFP_KERNEL); if (!secy->tx_sc.md_dst) /* macsec and secy percpu stats will be freed when unregistering * net_device in macsec_free_netdev() */ return -ENOMEM; if (sci == MACSEC_UNDEF_SCI) sci = dev_to_sci(dev, MACSEC_PORT_ES); secy->netdev = dev; secy->operational = true; secy->key_len = DEFAULT_SAK_LEN; secy->icv_len = icv_len; secy->validate_frames = MACSEC_VALIDATE_DEFAULT; secy->protect_frames = true; secy->replay_protect = false; secy->xpn = DEFAULT_XPN; secy->sci = sci; secy->tx_sc.md_dst->u.macsec_info.sci = sci; secy->tx_sc.active = true; secy->tx_sc.encoding_sa = DEFAULT_ENCODING_SA; secy->tx_sc.encrypt = DEFAULT_ENCRYPT; secy->tx_sc.send_sci = DEFAULT_SEND_SCI; secy->tx_sc.end_station = false; secy->tx_sc.scb = false; return 0; } static struct lock_class_key macsec_netdev_addr_lock_key; static int macsec_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macsec_dev *macsec = macsec_priv(dev); rx_handler_func_t *rx_handler; u8 icv_len = MACSEC_DEFAULT_ICV_LEN; struct net_device *real_dev; int err, mtu; sci_t sci; if (!tb[IFLA_LINK]) return -EINVAL; real_dev = __dev_get_by_index(net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev) return -ENODEV; if (real_dev->type != ARPHRD_ETHER) return -EINVAL; dev->priv_flags |= IFF_MACSEC; macsec->real_dev = real_dev; if (data && data[IFLA_MACSEC_OFFLOAD]) macsec->offload = nla_get_offload(data[IFLA_MACSEC_OFFLOAD]); else /* MACsec offloading is off by default */ macsec->offload = MACSEC_OFFLOAD_OFF; /* Check if the offloading mode is supported by the underlying layers */ if (macsec->offload != MACSEC_OFFLOAD_OFF && !macsec_check_offload(macsec->offload, macsec)) return -EOPNOTSUPP; /* send_sci must be set to true when transmit sci explicitly is set */ if ((data && data[IFLA_MACSEC_SCI]) && (data && data[IFLA_MACSEC_INC_SCI])) { u8 send_sci = !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]); if (!send_sci) return -EINVAL; } if (data && data[IFLA_MACSEC_ICV_LEN]) icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); mtu = real_dev->mtu - icv_len - macsec_extra_len(true); if (mtu < 0) dev->mtu = 0; else dev->mtu = mtu; rx_handler = rtnl_dereference(real_dev->rx_handler); if (rx_handler && rx_handler != macsec_handle_frame) return -EBUSY; err = register_netdevice(dev); if (err < 0) return err; netdev_lockdep_set_classes(dev); lockdep_set_class(&dev->addr_list_lock, &macsec_netdev_addr_lock_key); err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) goto unregister; /* need to be already registered so that ->init has run and * the MAC addr is set */ if (data && data[IFLA_MACSEC_SCI]) sci = nla_get_sci(data[IFLA_MACSEC_SCI]); else if (data && data[IFLA_MACSEC_PORT]) sci = dev_to_sci(dev, nla_get_be16(data[IFLA_MACSEC_PORT])); else sci = dev_to_sci(dev, MACSEC_PORT_ES); if (rx_handler && sci_exists(real_dev, sci)) { err = -EBUSY; goto unlink; } err = macsec_add_dev(dev, sci, icv_len); if (err) goto unlink; if (data) { err = macsec_changelink_common(dev, data); if (err) goto del_dev; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.secy = &macsec->secy; err = macsec_offload(ops->mdo_add_secy, &ctx); if (err) goto del_dev; macsec->insert_tx_tag = macsec_needs_tx_tag(macsec, ops); } } err = register_macsec_dev(real_dev, dev); if (err < 0) goto del_dev; netif_stacked_transfer_operstate(real_dev, dev); linkwatch_fire_event(dev); macsec_generation++; return 0; del_dev: macsec_del_dev(macsec); unlink: netdev_upper_dev_unlink(real_dev, dev); unregister: unregister_netdevice(dev); return err; } static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u64 csid = MACSEC_DEFAULT_CIPHER_ID; u8 icv_len = MACSEC_DEFAULT_ICV_LEN; int flag; bool es, scb, sci; if (!data) return 0; if (data[IFLA_MACSEC_CIPHER_SUITE]) csid = nla_get_u64(data[IFLA_MACSEC_CIPHER_SUITE]); if (data[IFLA_MACSEC_ICV_LEN]) { icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); if (icv_len != MACSEC_DEFAULT_ICV_LEN) { char dummy_key[DEFAULT_SAK_LEN] = { 0 }; struct crypto_aead *dummy_tfm; dummy_tfm = macsec_alloc_tfm(dummy_key, DEFAULT_SAK_LEN, icv_len); if (IS_ERR(dummy_tfm)) return PTR_ERR(dummy_tfm); crypto_free_aead(dummy_tfm); } } switch (csid) { case MACSEC_CIPHER_ID_GCM_AES_128: case MACSEC_CIPHER_ID_GCM_AES_256: case MACSEC_CIPHER_ID_GCM_AES_XPN_128: case MACSEC_CIPHER_ID_GCM_AES_XPN_256: case MACSEC_DEFAULT_CIPHER_ID: if (icv_len < MACSEC_MIN_ICV_LEN || icv_len > MACSEC_STD_ICV_LEN) return -EINVAL; break; default: return -EINVAL; } if (data[IFLA_MACSEC_ENCODING_SA]) { if (nla_get_u8(data[IFLA_MACSEC_ENCODING_SA]) >= MACSEC_NUM_AN) return -EINVAL; } for (flag = IFLA_MACSEC_ENCODING_SA + 1; flag < IFLA_MACSEC_VALIDATION; flag++) { if (data[flag]) { if (nla_get_u8(data[flag]) > 1) return -EINVAL; } } es = data[IFLA_MACSEC_ES] ? nla_get_u8(data[IFLA_MACSEC_ES]) : false; sci = data[IFLA_MACSEC_INC_SCI] ? nla_get_u8(data[IFLA_MACSEC_INC_SCI]) : false; scb = data[IFLA_MACSEC_SCB] ? nla_get_u8(data[IFLA_MACSEC_SCB]) : false; if ((sci && (scb || es)) || (scb && es)) return -EINVAL; if (data[IFLA_MACSEC_VALIDATION] && nla_get_u8(data[IFLA_MACSEC_VALIDATION]) > MACSEC_VALIDATE_MAX) return -EINVAL; if ((data[IFLA_MACSEC_REPLAY_PROTECT] && nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT])) && !data[IFLA_MACSEC_WINDOW]) return -EINVAL; return 0; } static struct net *macsec_get_link_net(const struct net_device *dev) { return dev_net(macsec_priv(dev)->real_dev); } struct net_device *macsec_get_real_dev(const struct net_device *dev) { return macsec_priv(dev)->real_dev; } EXPORT_SYMBOL_GPL(macsec_get_real_dev); bool macsec_netdev_is_offloaded(struct net_device *dev) { return macsec_is_offloaded(macsec_priv(dev)); } EXPORT_SYMBOL_GPL(macsec_netdev_is_offloaded); static size_t macsec_get_size(const struct net_device *dev) { return nla_total_size_64bit(8) + /* IFLA_MACSEC_SCI */ nla_total_size(1) + /* IFLA_MACSEC_ICV_LEN */ nla_total_size_64bit(8) + /* IFLA_MACSEC_CIPHER_SUITE */ nla_total_size(4) + /* IFLA_MACSEC_WINDOW */ nla_total_size(1) + /* IFLA_MACSEC_ENCODING_SA */ nla_total_size(1) + /* IFLA_MACSEC_ENCRYPT */ nla_total_size(1) + /* IFLA_MACSEC_PROTECT */ nla_total_size(1) + /* IFLA_MACSEC_INC_SCI */ nla_total_size(1) + /* IFLA_MACSEC_ES */ nla_total_size(1) + /* IFLA_MACSEC_SCB */ nla_total_size(1) + /* IFLA_MACSEC_REPLAY_PROTECT */ nla_total_size(1) + /* IFLA_MACSEC_VALIDATION */ nla_total_size(1) + /* IFLA_MACSEC_OFFLOAD */ 0; } static int macsec_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct macsec_tx_sc *tx_sc; struct macsec_dev *macsec; struct macsec_secy *secy; u64 csid; macsec = macsec_priv(dev); secy = &macsec->secy; tx_sc = &secy->tx_sc; switch (secy->key_len) { case MACSEC_GCM_AES_128_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_128 : MACSEC_DEFAULT_CIPHER_ID; break; case MACSEC_GCM_AES_256_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_256 : MACSEC_CIPHER_ID_GCM_AES_256; break; default: goto nla_put_failure; } if (nla_put_sci(skb, IFLA_MACSEC_SCI, secy->sci, IFLA_MACSEC_PAD) || nla_put_u8(skb, IFLA_MACSEC_ICV_LEN, secy->icv_len) || nla_put_u64_64bit(skb, IFLA_MACSEC_CIPHER_SUITE, csid, IFLA_MACSEC_PAD) || nla_put_u8(skb, IFLA_MACSEC_ENCODING_SA, tx_sc->encoding_sa) || nla_put_u8(skb, IFLA_MACSEC_ENCRYPT, tx_sc->encrypt) || nla_put_u8(skb, IFLA_MACSEC_PROTECT, secy->protect_frames) || nla_put_u8(skb, IFLA_MACSEC_INC_SCI, tx_sc->send_sci) || nla_put_u8(skb, IFLA_MACSEC_ES, tx_sc->end_station) || nla_put_u8(skb, IFLA_MACSEC_SCB, tx_sc->scb) || nla_put_u8(skb, IFLA_MACSEC_REPLAY_PROTECT, secy->replay_protect) || nla_put_u8(skb, IFLA_MACSEC_VALIDATION, secy->validate_frames) || nla_put_u8(skb, IFLA_MACSEC_OFFLOAD, macsec->offload) || 0) goto nla_put_failure; if (secy->replay_protect) { if (nla_put_u32(skb, IFLA_MACSEC_WINDOW, secy->replay_window)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops macsec_link_ops __read_mostly = { .kind = "macsec", .priv_size = sizeof(struct macsec_dev), .maxtype = IFLA_MACSEC_MAX, .policy = macsec_rtnl_policy, .setup = macsec_setup, .validate = macsec_validate_attr, .newlink = macsec_newlink, .changelink = macsec_changelink, .dellink = macsec_dellink, .get_size = macsec_get_size, .fill_info = macsec_fill_info, .get_link_net = macsec_get_link_net, }; static bool is_macsec_master(struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == macsec_handle_frame; } static int macsec_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *real_dev = netdev_notifier_info_to_dev(ptr); LIST_HEAD(head); if (!is_macsec_master(real_dev)) return NOTIFY_DONE; switch (event) { case NETDEV_DOWN: case NETDEV_UP: case NETDEV_CHANGE: { struct macsec_dev *m, *n; struct macsec_rxh_data *rxd; rxd = macsec_data_rtnl(real_dev); list_for_each_entry_safe(m, n, &rxd->secys, secys) { struct net_device *dev = m->secy.netdev; netif_stacked_transfer_operstate(real_dev, dev); } break; } case NETDEV_UNREGISTER: { struct macsec_dev *m, *n; struct macsec_rxh_data *rxd; rxd = macsec_data_rtnl(real_dev); list_for_each_entry_safe(m, n, &rxd->secys, secys) { macsec_common_dellink(m->secy.netdev, &head); } netdev_rx_handler_unregister(real_dev); kfree(rxd); unregister_netdevice_many(&head); break; } case NETDEV_CHANGEMTU: { struct macsec_dev *m; struct macsec_rxh_data *rxd; rxd = macsec_data_rtnl(real_dev); list_for_each_entry(m, &rxd->secys, secys) { struct net_device *dev = m->secy.netdev; unsigned int mtu = real_dev->mtu - (m->secy.icv_len + macsec_extra_len(true)); if (dev->mtu > mtu) dev_set_mtu(dev, mtu); } } } return NOTIFY_OK; } static struct notifier_block macsec_notifier = { .notifier_call = macsec_notify, }; static int __init macsec_init(void) { int err; pr_info("MACsec IEEE 802.1AE\n"); err = register_netdevice_notifier(&macsec_notifier); if (err) return err; err = rtnl_link_register(&macsec_link_ops); if (err) goto notifier; err = genl_register_family(&macsec_fam); if (err) goto rtnl; return 0; rtnl: rtnl_link_unregister(&macsec_link_ops); notifier: unregister_netdevice_notifier(&macsec_notifier); return err; } static void __exit macsec_exit(void) { genl_unregister_family(&macsec_fam); rtnl_link_unregister(&macsec_link_ops); unregister_netdevice_notifier(&macsec_notifier); rcu_barrier(); } module_init(macsec_init); module_exit(macsec_exit); MODULE_ALIAS_RTNL_LINK("macsec"); MODULE_ALIAS_GENL_FAMILY("macsec"); MODULE_DESCRIPTION("MACsec IEEE 802.1AE"); MODULE_LICENSE("GPL v2"); |
| 811 132 132 132 132 1 811 808 810 811 374 373 374 375 2 37 38 37 131 131 612 4 1 617 618 618 618 1013 616 131 131 131 131 131 131 131 131 131 131 131 1238 320 1006 1009 109 1009 1007 1005 1009 1006 131 1008 1071 1084 1086 1040 603 602 1 1 600 627 628 311 629 627 629 603 603 603 602 629 628 111 568 601 600 526 16 97 629 618 5 5 490 490 470 1298 361 1211 1208 1204 11 1188 1 1125 617 375 375 358 2643 2643 2642 2638 2640 2643 173 173 173 173 2642 2640 2643 942 942 826 824 10 10 10 10 1540 1515 6 33 16 16 763 173 173 173 173 601 1236 1237 1144 135 1237 1235 1237 1237 1235 1237 331 374 375 375 375 119 331 118 330 374 374 1138 1138 1137 1137 1137 656 1137 1136 1138 1138 1138 1138 1138 1137 1368 1370 1368 429 430 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. * * 10Apr2002 Andrew Morton * Initial version */ #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/init.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> #include <linux/mm_inline.h> #include <trace/events/writeback.h> #include "internal.h" /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ #define MAX_PAUSE max(HZ/5, 1) /* * Try to keep balance_dirty_pages() call intervals higher than this many pages * by raising pause time to max_pause when falls below it. */ #define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) /* * Estimate write bandwidth at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) #define RATELIMIT_CALC_SHIFT 10 /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ static long ratelimit_pages = 32; /* The following parameters are exported via /proc/sys/vm */ /* * Start background writeback (via writeback threads) at this percentage */ static int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of * dirty_background_ratio * the amount of dirtyable memory */ static unsigned long dirty_background_bytes; /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true */ static int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ static int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of * vm_dirty_ratio * the amount of dirtyable memory */ static unsigned long vm_dirty_bytes; /* * The interval between `kupdate'-style writebacks */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ EXPORT_SYMBOL_GPL(dirty_writeback_interval); /* * The longest time for which data is allowed to remain dirty */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ int laptop_mode; EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ struct wb_domain global_wb_domain; /* consolidated parameters for balance_dirty_pages() and its subroutines */ struct dirty_throttle_control { #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *dom; struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ #endif struct bdi_writeback *wb; struct fprop_local_percpu *wb_completions; unsigned long avail; /* dirtyable */ unsigned long dirty; /* file_dirty + write + nfs */ unsigned long thresh; /* dirty threshold */ unsigned long bg_thresh; /* dirty background threshold */ unsigned long wb_dirty; /* per-wb counterparts */ unsigned long wb_thresh; unsigned long wb_bg_thresh; unsigned long pos_ratio; bool freerun; bool dirty_exceeded; }; /* * Length of period for aging writeout fractions of bdis. This is an * arbitrarily chosen number. The longer the period, the slower fractions will * reflect changes in current writeout rate. */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) #ifdef CONFIG_CGROUP_WRITEBACK #define GDTC_INIT(__wb) .wb = (__wb), \ .dom = &global_wb_domain, \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB .dom = &global_wb_domain #define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ .dom = mem_cgroup_wb_domain(__wb), \ .wb_completions = &(__wb)->memcg_completions, \ .gdtc = __gdtc static bool mdtc_valid(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return mdtc->gdtc; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return &wb->memcg_completions; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { unsigned long this_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); unsigned long long min = wb->bdi->min_ratio; unsigned long long max = wb->bdi->max_ratio; /* * @wb may already be clean by the time control reaches here and * the total may not include its bw. */ if (this_bw < tot_bw) { if (min) { min *= this_bw; min = div64_ul(min, tot_bw); } if (max < 100 * BDI_RATIO_SCALE) { max *= this_bw; max = div64_ul(max, tot_bw); } } *minp = min; *maxp = max; } #else /* CONFIG_CGROUP_WRITEBACK */ #define GDTC_INIT(__wb) .wb = (__wb), \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB #define MDTC_INIT(__wb, __gdtc) static bool mdtc_valid(struct dirty_throttle_control *dtc) { return false; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return &global_wb_domain; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return NULL; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return NULL; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { *minp = wb->bdi->min_ratio; *maxp = wb->bdi->max_ratio; } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect * lowmem and the ability to uphold the zone's watermarks without * requiring writeback. * * This number of dirtyable pages is the base value of which the * user-configurable dirty ratio is the effective number of pages that * are allowed to be actually dirtied. Per individual zone, or * globally by using the sum of dirtyable pages over all zones. * * Because the user is allowed to specify the dirty limit globally as * absolute number of bytes, calculating the per-zone dirty limit can * require translating the configured limit into a percentage of * global dirtyable memory first. */ /** * node_dirtyable_memory - number of dirtyable pages in a node * @pgdat: the node * * Return: the node's number of pages potentially available for dirty * page cache. This is the base value for the per-node dirty limits. */ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { unsigned long nr_pages = 0; int z; for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; nr_pages += zone_page_state(zone, NR_FREE_PAGES); } /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ nr_pages -= min(nr_pages, pgdat->totalreserve_pages); nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; int i; for_each_node_state(node, N_HIGH_MEMORY) { for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { struct zone *z; unsigned long nr_pages; if (!is_highmem_idx(i)) continue; z = &NODE_DATA(node)->node_zones[i]; if (!populated_zone(z)) continue; nr_pages = zone_page_state(z, NR_FREE_PAGES); /* watch for underflows */ nr_pages -= min(nr_pages, high_wmark_pages(z)); nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); x += nr_pages; } } /* * Make sure that the number of highmem pages is never larger * than the number of the total dirtyable memory. This can only * occur in very strange VM situations but we want to make sure * that this does not occur. */ return min(x, total); #else return 0; #endif } /** * global_dirtyable_memory - number of globally dirtyable pages * * Return: the global number of pages potentially available for dirty * page cache. This is the base value for the global dirty limits. */ static unsigned long global_dirtyable_memory(void) { unsigned long x; x = global_zone_page_state(NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ x -= min(x, totalreserve_pages); x += global_node_page_state(NR_INACTIVE_FILE); x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); return x + 1; /* Ensure that we never return 0 */ } /** * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain * @dtc: dirty_throttle_control of interest * * Calculate @dtc->thresh and ->bg_thresh considering * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller * must ensure that @dtc->avail is set before calling this function. The * dirty limits will be lifted by 1/4 for real-time tasks. */ static void domain_dirty_limits(struct dirty_throttle_control *dtc) { const unsigned long available_memory = dtc->avail; struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); unsigned long bytes = vm_dirty_bytes; unsigned long bg_bytes = dirty_background_bytes; /* convert ratios to per-PAGE_SIZE for higher precision */ unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; unsigned long thresh; unsigned long bg_thresh; struct task_struct *tsk; /* gdtc is !NULL iff @dtc is for memcg domain */ if (gdtc) { unsigned long global_avail = gdtc->avail; /* * The byte settings can't be applied directly to memcg * domains. Convert them to ratios by scaling against * globally available memory. As the ratios are in * per-PAGE_SIZE, they can be obtained by dividing bytes by * number of pages. */ if (bytes) ratio = min(DIV_ROUND_UP(bytes, global_avail), PAGE_SIZE); if (bg_bytes) bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), PAGE_SIZE); bytes = bg_bytes = 0; } if (bytes) thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else thresh = (ratio * available_memory) / PAGE_SIZE; if (bg_bytes) bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; tsk = current; if (rt_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } /* * Dirty throttling logic assumes the limits in page units fit into * 32-bits. This gives 16TB dirty limits max which is hopefully enough. */ if (thresh > UINT_MAX) thresh = UINT_MAX; /* This makes sure bg_thresh is within 32-bits as well */ if (bg_thresh >= thresh) bg_thresh = thresh / 2; dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; /* we should eventually report the domain in the TP */ if (!gdtc) trace_global_dirty_state(bg_thresh, thresh); } /** * global_dirty_limits - background-writeback and dirty-throttling thresholds * @pbackground: out parameter for bg_thresh * @pdirty: out parameter for thresh * * Calculate bg_thresh and thresh for global_wb_domain. See * domain_dirty_limits() for details. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; gdtc.avail = global_dirtyable_memory(); domain_dirty_limits(&gdtc); *pbackground = gdtc.bg_thresh; *pdirty = gdtc.thresh; } /** * node_dirty_limit - maximum number of dirty pages allowed in a node * @pgdat: the node * * Return: the maximum number of dirty pages allowed in a node, based * on the node's dirtyable memory. */ static unsigned long node_dirty_limit(struct pglist_data *pgdat) { unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * node_memory / global_dirtyable_memory(); else dirty = vm_dirty_ratio * node_memory / 100; if (rt_task(tsk)) dirty += dirty / 4; /* * Dirty throttling logic assumes the limits in page units fit into * 32-bits. This gives 16TB dirty limits max which is hopefully enough. */ return min_t(unsigned long, dirty, UINT_MAX); } /** * node_dirty_ok - tells whether a node is within its dirty limits * @pgdat: the node to check * * Return: %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ bool node_dirty_ok(struct pglist_data *pgdat) { unsigned long limit = node_dirty_limit(pgdat); unsigned long nr_pages = 0; nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); nr_pages += node_page_state(pgdat, NR_WRITEBACK); return nr_pages <= limit; } #ifdef CONFIG_SYSCTL static int dirty_background_ratio_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } static int dirty_background_bytes_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; unsigned long old_bytes = dirty_background_bytes; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) { if (DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE) > UINT_MAX) { dirty_background_bytes = old_bytes; return -ERANGE; } dirty_background_ratio = 0; } return ret; } static int dirty_ratio_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { writeback_set_ratelimit(); vm_dirty_bytes = 0; } return ret; } static int dirty_bytes_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { if (DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) > UINT_MAX) { vm_dirty_bytes = old_bytes; return -ERANGE; } writeback_set_ratelimit(); vm_dirty_ratio = 0; } return ret; } #endif static unsigned long wp_next_time(unsigned long cur_time) { cur_time += VM_COMPLETIONS_PERIOD_LEN; /* 0 has a special meaning... */ if (!cur_time) return 1; return cur_time; } static void wb_domain_writeout_add(struct wb_domain *dom, struct fprop_local_percpu *completions, unsigned int max_prop_frac, long nr) { __fprop_add_percpu_max(&dom->completions, completions, max_prop_frac, nr); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* * We can race with other __bdi_writeout_inc calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. */ dom->period_time = wp_next_time(jiffies); mod_timer(&dom->period_timer, dom->period_time); } } /* * Increment @wb's writeout completion count and the global writeout * completion count. Called from __folio_end_writeback(). */ static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr) { struct wb_domain *cgdom; wb_stat_mod(wb, WB_WRITTEN, nr); wb_domain_writeout_add(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac, nr); cgdom = mem_cgroup_wb_domain(wb); if (cgdom) wb_domain_writeout_add(cgdom, wb_memcg_completions(wb), wb->bdi->max_prop_frac, nr); } void wb_writeout_inc(struct bdi_writeback *wb) { unsigned long flags; local_irq_save(flags); __wb_writeout_add(wb, 1); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use * deferred timers so count with missed periods. */ static void writeout_period(struct timer_list *t) { struct wb_domain *dom = from_timer(dom, t, period_timer); int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; if (fprop_new_period(&dom->completions, miss_periods + 1)) { dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ dom->period_time = 0; } } int wb_domain_init(struct wb_domain *dom, gfp_t gfp) { memset(dom, 0, sizeof(*dom)); spin_lock_init(&dom->lock); timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE); dom->dirty_limit_tstamp = jiffies; return fprop_global_init(&dom->completions, gfp); } #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom) { del_timer_sync(&dom->period_timer); fprop_global_destroy(&dom->completions); } #endif /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not * exceed 100%. */ static unsigned int bdi_min_ratio; static int bdi_check_pages_limit(unsigned long pages) { unsigned long max_dirty_pages = global_dirtyable_memory(); if (pages > max_dirty_pages) return -EINVAL; return 0; } static unsigned long bdi_ratio_from_pages(unsigned long pages) { unsigned long background_thresh; unsigned long dirty_thresh; unsigned long ratio; global_dirty_limits(&background_thresh, &dirty_thresh); ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh); return ratio; } static u64 bdi_get_bytes(unsigned int ratio) { unsigned long background_thresh; unsigned long dirty_thresh; u64 bytes; global_dirty_limits(&background_thresh, &dirty_thresh); bytes = (dirty_thresh * PAGE_SIZE * ratio) / BDI_RATIO_SCALE / 100; return bytes; } static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { unsigned int delta; int ret = 0; if (min_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { if (min_ratio < bdi->min_ratio) { delta = bdi->min_ratio - min_ratio; bdi_min_ratio -= delta; bdi->min_ratio = min_ratio; } else { delta = min_ratio - bdi->min_ratio; if (bdi_min_ratio + delta < 100 * BDI_RATIO_SCALE) { bdi_min_ratio += delta; bdi->min_ratio = min_ratio; } else { ret = -EINVAL; } } } spin_unlock_bh(&bdi_lock); return ret; } static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { int ret = 0; if (max_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / (100 * BDI_RATIO_SCALE); } spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio); } int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio * BDI_RATIO_SCALE); } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio * BDI_RATIO_SCALE); } EXPORT_SYMBOL(bdi_set_max_ratio); u64 bdi_get_min_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->min_ratio); } int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes) { int ret; unsigned long pages = min_bytes >> PAGE_SHIFT; unsigned long min_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; min_ratio = bdi_ratio_from_pages(pages); return __bdi_set_min_ratio(bdi, min_ratio); } u64 bdi_get_max_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->max_ratio); } int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes) { int ret; unsigned long pages = max_bytes >> PAGE_SHIFT; unsigned long max_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; max_ratio = bdi_ratio_from_pages(pages); return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit) { if (strict_limit > 1) return -EINVAL; spin_lock_bh(&bdi_lock); if (strict_limit) bdi->capabilities |= BDI_CAP_STRICTLIMIT; else bdi->capabilities &= ~BDI_CAP_STRICTLIMIT; spin_unlock_bh(&bdi_lock); return 0; } static unsigned long dirty_freerun_ceiling(unsigned long thresh, unsigned long bg_thresh) { return (thresh + bg_thresh) / 2; } static unsigned long hard_dirty_limit(struct wb_domain *dom, unsigned long thresh) { return max(thresh, dom->dirty_limit); } /* * Memory which can be further allocated to a memcg domain is capped by * system-wide clean memory excluding the amount being used in the domain. */ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, unsigned long filepages, unsigned long headroom) { struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); unsigned long clean = filepages - min(filepages, mdtc->dirty); unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); unsigned long other_clean = global_clean - min(global_clean, clean); mdtc->avail = filepages + min(headroom, other_clean); } static inline bool dtc_is_global(struct dirty_throttle_control *dtc) { return mdtc_gdtc(dtc) == NULL; } /* * Dirty background will ignore pages being written as we're trying to * decide whether to put more under writeback. */ static void domain_dirty_avail(struct dirty_throttle_control *dtc, bool include_writeback) { if (dtc_is_global(dtc)) { dtc->avail = global_dirtyable_memory(); dtc->dirty = global_node_page_state(NR_FILE_DIRTY); if (include_writeback) dtc->dirty += global_node_page_state(NR_WRITEBACK); } else { unsigned long filepages = 0, headroom = 0, writeback = 0; mem_cgroup_wb_stats(dtc->wb, &filepages, &headroom, &dtc->dirty, &writeback); if (include_writeback) dtc->dirty += writeback; mdtc_calc_avail(dtc, filepages, headroom); } } /** * __wb_calc_thresh - @wb's share of dirty threshold * @dtc: dirty_throttle_context of interest * @thresh: dirty throttling or dirty background threshold of wb_domain in @dtc * * Note that balance_dirty_pages() will only seriously take dirty throttling * threshold as a hard limit when sleeping max_pause per page is not enough * to keep the dirty pages under control. For example, when the device is * completely stalled due to some error conditions, or when there are 1000 * dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * * Return: @wb's dirty limit in pages. For dirty throttling limit, the term * "dirty" in the context of dirty balancing includes all PG_dirty and * PG_writeback pages. */ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc, unsigned long thresh) { struct wb_domain *dom = dtc_dom(dtc); u64 wb_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; /* * Calculate this wb's share of the thresh ratio. */ fprop_fraction_percpu(&dom->completions, dtc->wb_completions, &numerator, &denominator); wb_thresh = (thresh * (100 * BDI_RATIO_SCALE - bdi_min_ratio)) / (100 * BDI_RATIO_SCALE); wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE); if (wb_thresh > (thresh * wb_max_ratio) / (100 * BDI_RATIO_SCALE)) wb_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); return wb_thresh; } unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; return __wb_calc_thresh(&gdtc, thresh); } unsigned long cgwb_calc_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) }; domain_dirty_avail(&gdtc, true); domain_dirty_avail(&mdtc, true); domain_dirty_limits(&mdtc); return __wb_calc_thresh(&mdtc, mdtc.thresh); } /* * setpoint - dirty 3 * f(dirty) := 1.0 + (----------------) * limit - setpoint * * it's a 3rd order polynomial that subjects to * * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast * (2) f(setpoint) = 1.0 => the balance point * (3) f(limit) = 0 => the hard limit * (4) df/dx <= 0 => negative feedback control * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, (limit - setpoint) | 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio += 1 << RATELIMIT_CALC_SHIFT; return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); } /* * Dirty position control. * * (o) global/bdi setpoints * * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. * * pos_ratio = 1 << RATELIMIT_CALC_SHIFT * * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * * if (wb_dirty < wb_setpoint) scale up pos_ratio * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * * (o) global control line * * ^ pos_ratio * | * | |<===== global dirty control scope ======>| * 2.0 * * * * * * * * | .* * | . * * | . * * | . * * | . * * | . * * 1.0 ................................* * | . . * * | . . * * | . . * * | . . * * | . . * * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * * (o) wb control line * * ^ pos_ratio * | * | * * | * * | * * | * * | * |<=========== span ============>| * 1.0 .......................* * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * 1/4 ...............................................* * * * * * * * * * * * * | . . * | . . * | . . * 0 +----------------------.-------------------------------.-------------> * wb_setpoint^ x_intercept^ * * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD * card's wb_dirty may rush to many times higher than wb_setpoint. * - the wb dirty thresh drops quickly due to change of JBOD workload */ static void wb_position_ratio(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; dtc->pos_ratio = 0; if (unlikely(dtc->dirty >= limit)) return; /* * global setpoint * * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For * such filesystems balance_dirty_pages always checks wb counters * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. Without strictlimit feature, fuse writeback may * consume arbitrary amount of RAM because it is accounted in * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * * Here, in wb_position_ratio(), we calculate pos_ratio based on * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { long long wb_pos_ratio; if (dtc->wb_dirty < 8) { dtc->pos_ratio = min_t(long long, pos_ratio * 2, 2 << RATELIMIT_CALC_SHIFT); return; } if (dtc->wb_dirty >= wb_thresh) return; wb_setpoint = dirty_freerun_ceiling(wb_thresh, dtc->wb_bg_thresh); if (wb_setpoint == 0 || wb_setpoint == wb_thresh) return; wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, wb_thresh); /* * Typically, for strictlimit case, wb_setpoint << setpoint * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other * wb's) while given strictlimit wb is below limit. * * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); return; } /* * We have computed basic pos_ratio above based on global situation. If * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* * wb setpoint * * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * * x_intercept - wb_dirty * := -------------------------- * x_intercept - wb_setpoint * * The main wb control line is a linear function that subjects to * * (1) f(wb_setpoint) = 1.0 * (2) k = - 1 / (8 * write_bw) (in single wb case) * or equally: x_intercept = wb_setpoint + 8 * write_bw * * For single wb case, the dirty pages are observed to fluctuate * regularly within range * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ if (unlikely(wb_thresh > dtc->thresh)) wb_thresh = dtc->thresh; /* * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); /* * scale global setpoint to wb's: * wb_setpoint = setpoint * wb_thresh / thresh */ x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); wb_setpoint = setpoint * (u64)x >> 16; /* * Use span=(8*write_bw) in single wb case as indicated by * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * * wb_thresh thresh - wb_thresh * span = --------- * (8 * write_bw) + ------------------ * wb_thresh * thresh thresh */ span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; x_intercept = wb_setpoint + span; if (dtc->wb_dirty < x_intercept - span / 4) { pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ x_intercept = wb_thresh / 2; if (dtc->wb_dirty < x_intercept) { if (dtc->wb_dirty > x_intercept / 8) pos_ratio = div_u64(pos_ratio * x_intercept, dtc->wb_dirty); else pos_ratio *= 8; } dtc->pos_ratio = pos_ratio; } static void wb_update_write_bandwidth(struct bdi_writeback *wb, unsigned long elapsed, unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); unsigned long avg = wb->avg_write_bandwidth; unsigned long old = wb->write_bandwidth; u64 bw; /* * bw = written * HZ / elapsed * * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period * * @written may have decreased due to folio_redirty_for_writepage(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { bw = div64_ul(bw, elapsed); avg = bw; goto out; } bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* * one more level of smoothing, for filtering out sudden spikes */ if (avg > old && old >= (unsigned long)bw) avg -= (avg - old) >> 3; if (avg < old && old <= (unsigned long)bw) avg += (old - avg) >> 3; out: /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ avg = max(avg, 1LU); if (wb_has_dirty_io(wb)) { long delta = avg - wb->avg_write_bandwidth; WARN_ON_ONCE(atomic_long_add_return(delta, &wb->bdi->tot_write_bandwidth) <= 0); } wb->write_bandwidth = bw; WRITE_ONCE(wb->avg_write_bandwidth, avg); } static void update_dirty_limit(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; unsigned long limit = dom->dirty_limit; /* * Follow up in one step. */ if (limit < thresh) { limit = thresh; goto update; } /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: dom->dirty_limit = limit; } static void domain_update_dirty_limit(struct dirty_throttle_control *dtc, unsigned long now) { struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; spin_lock(&dom->lock); if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { update_dirty_limit(dtc); dom->dirty_limit_tstamp = now; } spin_unlock(&dom->lock); } /* * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long dirtied, unsigned long elapsed) { struct bdi_writeback *wb = dtc->wb; unsigned long dirty = dtc->dirty; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; unsigned long step; unsigned long x; unsigned long shift; /* * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * * Note that the expanded form is not a pure rate feedback: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) * but also takes pos_ratio into account: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) * * (1) is not realistic because pos_ratio also takes part in balancing * the dirty rate. Consider the state * pos_ratio = 0.5 (3) * rate = 2 * (write_bw / N) (4) * If (1) is used, it will stuck in that state! Because each dd will * be throttled at * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) * yielding * dirty_rate = N * task_ratelimit = write_bw (6) * put (6) into (1) we get * rate_(i+1) = rate_(i) (7) * * So we end up using (2) to always keep * rate_(i+1) ~= (write_bw / N) (8) * regardless of the value of pos_ratio. As long as (8) is satisfied, * pos_ratio is able to drive itself to 1.0, which is not only where * the dirty count meet the setpoint, but also where the slope of * pos_ratio is most flat and hence task_ratelimit is least fluctuated. */ balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, dirty_rate | 1); /* * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw */ if (unlikely(balanced_dirty_ratelimit > write_bw)) balanced_dirty_ratelimit = write_bw; /* * We could safely do this and return immediately: * * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and * limit the step size. * * The below code essentially only uses the relative value of * * task_ratelimit - dirty_ratelimit * = (pos_ratio - 1) * dirty_ratelimit * * which reflects the direction and size of dirty position error. */ /* * dirty_ratelimit will follow balanced_dirty_ratelimit iff * task_ratelimit is on the same side of dirty_ratelimit, too. * For example, when * - dirty_ratelimit > balanced_dirty_ratelimit * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) * lowering dirty_ratelimit will help meet both the position and rate * control targets. Otherwise, don't update dirty_ratelimit if it will * only help meet the rate target. After all, what the users ultimately * feel and care are stable dirty rate and small position error. * * |task_ratelimit - dirty_ratelimit| is used to limit the step size * and filter out the singular points of balanced_dirty_ratelimit. Which * keeps jumping around randomly and can even leap far away at times * due to the small 200ms estimation period of dirty_rate (we want to * keep that period small to reduce time lags). */ step = 0; /* * For strictlimit case, calculations above were based on wb counters * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). * Hence, to calculate "step" properly, we have to use wb_dirty as * "dirty" and wb_setpoint as "setpoint". * * We rampup dirty_ratelimit forcibly if wb_dirty is low because * it's possible that wb_thresh is close to zero due to inactivity * of backing device. */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { dirty = dtc->wb_dirty; if (dtc->wb_dirty < 8) setpoint = dtc->wb_dirty + 1; else setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; } /* * Don't pursue 100% rate matching. It's impossible since the balanced * rate itself is constantly fluctuating. So decrease the track speed * when it gets close to the target. Helps eliminate pointless tremors. */ shift = dirty_ratelimit / (2 * step + 1); if (shift < BITS_PER_LONG) step = DIV_ROUND_UP(step >> shift, 8); else step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; else dirty_ratelimit -= step; WRITE_ONCE(wb->dirty_ratelimit, max(dirty_ratelimit, 1UL)); wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit); } static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, struct dirty_throttle_control *mdtc, bool update_ratelimit) { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; unsigned long elapsed; unsigned long dirtied; unsigned long written; spin_lock(&wb->list_lock); /* * Lockless checks for elapsed time are racy and delayed update after * IO completion doesn't do it at all (to make sure written pages are * accounted reasonably quickly). Make sure elapsed >= 1 to avoid * division errors. */ elapsed = max(now - wb->bw_time_stamp, 1UL); dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); if (update_ratelimit) { domain_update_dirty_limit(gdtc, now); wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); /* * @mdtc is always NULL if !CGROUP_WRITEBACK but the * compiler has no way to figure that out. Help it. */ if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { domain_update_dirty_limit(mdtc, now); wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); } } wb_update_write_bandwidth(wb, elapsed, written); wb->dirtied_stamp = dirtied; wb->written_stamp = written; WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } void wb_update_bandwidth(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; __wb_update_bandwidth(&gdtc, NULL, false); } /* Interval after which we consider wb idle and don't estimate bandwidth */ #define WB_BANDWIDTH_IDLE_JIF (HZ) static void wb_bandwidth_estimate_start(struct bdi_writeback *wb) { unsigned long now = jiffies; unsigned long elapsed = now - READ_ONCE(wb->bw_time_stamp); if (elapsed > WB_BANDWIDTH_IDLE_JIF && !atomic_read(&wb->writeback_inodes)) { spin_lock(&wb->list_lock); wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED); wb->written_stamp = wb_stat(wb, WB_WRITTEN); WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } } /* * After a task dirtied this many pages, balance_dirty_pages_ratelimited() * will look to see if it needs to start dirty throttling. * * If dirty_poll_interval is too low, big NUMA machines will call the expensive * global_zone_page_state() too often. So scale it near-sqrt to the safety margin * (the number of pages we may dirty without exceeding the dirty limits). */ static unsigned long dirty_poll_interval(unsigned long dirty, unsigned long thresh) { if (thresh > dirty) return 1UL << (ilog2(thresh - dirty) >> 1); return 1; } static unsigned long wb_max_pause(struct bdi_writeback *wb, unsigned long wb_dirty) { unsigned long bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long * time, a small pool of dirty/writeback pages may go empty and disk go * idle. * * 8 serves as the safety ratio. */ t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause) { long hi = ilog2(READ_ONCE(wb->avg_write_bandwidth)); long lo = ilog2(READ_ONCE(wb->dirty_ratelimit)); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ /* target for 10ms pause on 1-dd case */ t = max(1, HZ / 100); /* * Scale up pause time for concurrent dirtiers in order to reduce CPU * overheads. * * (N * 10ms) on 2^N concurrent tasks. */ if (hi > lo) t += (hi - lo) * (10 * HZ) / 1024; /* * This is a bit convoluted. We try to base the next nr_dirtied_pause * on the much more stable dirty_ratelimit. However the next pause time * will be computed based on task_ratelimit and the two rate limits may * depart considerably at some time. Especially if task_ratelimit goes * below dirty_ratelimit/2 and the target pause is max_pause, the next * pause time will be max_pause*2 _trimmed down_ to max_pause. As a * result task_ratelimit won't be executed faithfully, which could * eventually bring down dirty_ratelimit. * * We apply two rules to fix it up: * 1) try to estimate the next pause time and if necessary, use a lower * nr_dirtied_pause so as not to exceed max_pause. When this happens, * nr_dirtied_pause will be "dancing" with task_ratelimit. * 2) limit the target pause time to max_pause/2, so that the normal * small fluctuations of task_ratelimit won't trigger rule (1) and * nr_dirtied_pause will remain as stable as dirty_ratelimit. */ t = min(t, 1 + max_pause / 2); pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); /* * Tiny nr_dirtied_pause is found to hurt I/O performance in the test * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}. * When the 16 consecutive reads are often interrupted by some dirty * throttling pause during the async writes, cfq will go into idles * (deadline is fine). So push nr_dirtied_pause as high as possible * until reaches DIRTY_POLL_THRESH=32 pages. */ if (pages < DIRTY_POLL_THRESH) { t = max_pause; pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); if (pages > DIRTY_POLL_THRESH) { pages = DIRTY_POLL_THRESH; t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit; } } pause = HZ * pages / (task_ratelimit + 1); if (pause > max_pause) { t = max_pause; pages = task_ratelimit * t / roundup_pow_of_two(HZ); } *nr_dirtied_pause = pages; /* * The minimal pause time will normally be half the target pause time. */ return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long wb_reclaimable; /* * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow * go into state (wb_dirty >> wb_thresh) either because * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key * dirtiers for 100 seconds until wb_dirty drops under * wb_thresh. Instead the auxiliary wb control line in * wb_position_ratio() will let the dirtier task progress * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ dtc->wb_thresh = __wb_calc_thresh(dtc, dtc->thresh); dtc->wb_bg_thresh = dtc->thresh ? div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (dtc->wb_thresh < 2 * wb_stat_error()) { wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } static unsigned long domain_poll_intv(struct dirty_throttle_control *dtc, bool strictlimit) { unsigned long dirty, thresh; if (strictlimit) { dirty = dtc->wb_dirty; thresh = dtc->wb_thresh; } else { dirty = dtc->dirty; thresh = dtc->thresh; } return dirty_poll_interval(dirty, thresh); } /* * Throttle it only when the background writeback cannot catch-up. This avoids * (excessively) small writeouts when the wb limits are ramping up in case of * !strictlimit. * * In strictlimit case make decision based on the wb counters and limits. Small * writeouts when the wb limits are ramping up are the price we consciously pay * for strictlimit-ing. */ static void domain_dirty_freerun(struct dirty_throttle_control *dtc, bool strictlimit) { unsigned long dirty, thresh, bg_thresh; if (unlikely(strictlimit)) { wb_dirty_limits(dtc); dirty = dtc->wb_dirty; thresh = dtc->wb_thresh; bg_thresh = dtc->wb_bg_thresh; } else { dirty = dtc->dirty; thresh = dtc->thresh; bg_thresh = dtc->bg_thresh; } dtc->freerun = dirty <= dirty_freerun_ceiling(thresh, bg_thresh); } static void balance_domain_limits(struct dirty_throttle_control *dtc, bool strictlimit) { domain_dirty_avail(dtc, true); domain_dirty_limits(dtc); domain_dirty_freerun(dtc, strictlimit); } static void wb_dirty_freerun(struct dirty_throttle_control *dtc, bool strictlimit) { dtc->freerun = false; /* was already handled in domain_dirty_freerun */ if (strictlimit) return; wb_dirty_limits(dtc); /* * LOCAL_THROTTLE tasks must not be throttled when below the per-wb * freerun ceiling. */ if (!(current->flags & PF_LOCAL_THROTTLE)) return; dtc->freerun = dtc->wb_dirty < dirty_freerun_ceiling(dtc->wb_thresh, dtc->wb_bg_thresh); } static inline void wb_dirty_exceeded(struct dirty_throttle_control *dtc, bool strictlimit) { dtc->dirty_exceeded = (dtc->wb_dirty > dtc->wb_thresh) && ((dtc->dirty > dtc->thresh) || strictlimit); } /* * The limits fields dirty_exceeded and pos_ratio won't be updated if wb is * in freerun state. Please don't use these invalid fields in freerun case. */ static void balance_wb_limits(struct dirty_throttle_control *dtc, bool strictlimit) { wb_dirty_freerun(dtc, strictlimit); if (dtc->freerun) return; wb_dirty_exceeded(dtc, strictlimit); wb_position_ratio(dtc); } /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static int balance_dirty_pages(struct bdi_writeback *wb, unsigned long pages_dirtied, unsigned int flags) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; unsigned long nr_dirty; long period; long pause; long max_pause; long min_pause; int nr_dirtied_pause; unsigned long task_ratelimit; unsigned long dirty_ratelimit; struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; int ret = 0; for (;;) { unsigned long now = jiffies; nr_dirty = global_node_page_state(NR_FILE_DIRTY); balance_domain_limits(gdtc, strictlimit); if (mdtc) { /* * If @wb belongs to !root memcg, repeat the same * basic calculations for the memcg domain. */ balance_domain_limits(mdtc, strictlimit); } /* * In laptop mode, we wait until hitting the higher threshold * before starting background writeout, and then write out all * the way down to the lower threshold. So slow writers cause * minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if (!laptop_mode && nr_dirty > gdtc->bg_thresh && !writeback_in_progress(wb)) wb_start_background_writeback(wb); /* * If memcg domain is in effect, @dirty should be under * both global and memcg freerun ceilings. */ if (gdtc->freerun && (!mdtc || mdtc->freerun)) { unsigned long intv; unsigned long m_intv; free_running: intv = domain_poll_intv(gdtc, strictlimit); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = domain_poll_intv(mdtc, strictlimit); current->nr_dirtied_pause = min(intv, m_intv); break; } /* Start writeback even when in laptop mode */ if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ balance_wb_limits(gdtc, strictlimit); if (gdtc->freerun) goto free_running; sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ balance_wb_limits(mdtc, strictlimit); if (mdtc->freerun) goto free_running; if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; } wb->dirty_exceeded = gdtc->dirty_exceeded || (mdtc && mdtc->dirty_exceeded); if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) __wb_update_bandwidth(gdtc, mdtc, true); /* throttle according to the chosen dtc */ dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit); task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; max_pause = wb_max_pause(wb, sdtc->wb_dirty); min_pause = wb_min_pause(wb, max_pause, task_ratelimit, dirty_ratelimit, &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; pause = max_pause; goto pause; } period = HZ * pages_dirtied / task_ratelimit; pause = period; if (current->dirty_paused_when) pause -= now - current->dirty_paused_when; /* * For less than 1s think time (ext3/4 may block the dirtier * for up to 800ms from time to time on 1-HDD; so does xfs, * however at much less frequency), try to compensate it in * future periods by updating the virtual time; otherwise just * do a reset, as it may be a light dirtier. */ if (pause < min_pause) { trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, min(pause, 0L), start_time); if (pause < -HZ) { current->dirty_paused_when = now; current->nr_dirtied = 0; } else if (period) { current->dirty_paused_when += period; current->nr_dirtied = 0; } else if (current->nr_dirtied_pause <= pages_dirtied) current->nr_dirtied_pause += pages_dirtied; break; } if (unlikely(pause > max_pause)) { /* for occasional dropped task_ratelimit */ now += min(pause - max_pause, max_pause); pause = max_pause; } pause: trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, pause, start_time); if (flags & BDP_ASYNC) { ret = -EAGAIN; break; } __set_current_state(TASK_KILLABLE); bdi->last_bdp_sleep = jiffies; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; current->nr_dirtied = 0; current->nr_dirtied_pause = nr_dirtied_pause; /* * This is typically equal to (dirty < thresh) and can also * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponsive NFS server and the NFS dirty * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * * In theory 1 page is enough to keep the consumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 * more page. However wb_dirty has accounting errors. So use * the larger and more IO friendly wb_stat_error. */ if (sdtc->wb_dirty <= wb_stat_error()) break; if (fatal_signal_pending(current)) break; } return ret; } static DEFINE_PER_CPU(int, bdp_ratelimits); /* * Normal tasks are throttled by * loop { * dirty tsk->nr_dirtied_pause pages; * take a snap in balance_dirty_pages(); * } * However there is a worst case. If every task exit immediately when dirtied * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be * called to throttle the page dirties. The solution is to save the not yet * throttled page dirties in dirty_throttle_leaks on task exit and charge them * randomly into the running tasks. This works well for the above worst case, * as the new task will pick up and accumulate the old task's leaked dirty * count and eventually get throttled. */ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; /** * balance_dirty_pages_ratelimited_flags - Balance dirty memory state. * @mapping: address_space which was dirtied. * @flags: BDP flags. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * See balance_dirty_pages_ratelimited() for details. * * Return: If @flags contains BDP_ASYNC, it may return -EAGAIN to * indicate that memory is out of balance and the caller must wait * for I/O to complete. Otherwise, it will return 0 to indicate * that either memory was already in balance, or it was able to sleep * until the amount of dirty memory returned to balance. */ int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, unsigned int flags) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; int ratelimit; int ret = 0; int *p; if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) return ret; if (inode_cgwb_enabled(inode)) wb = wb_get_create_current(bdi, GFP_KERNEL); if (!wb) wb = &bdi->wb; ratelimit = current->nr_dirtied_pause; if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); /* * This prevents one CPU to accumulate too many dirtied pages without * calling into balance_dirty_pages(), which can happen when there are * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { *p = 0; ratelimit = 0; } /* * Pick up the dirtied pages by the exited tasks. This avoids lots of * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); *p -= nr_pages_dirtied; current->nr_dirtied += nr_pages_dirtied; } preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) ret = balance_dirty_pages(wb, current->nr_dirtied, flags); wb_put(wb); return ret; } EXPORT_SYMBOL_GPL(balance_dirty_pages_ratelimited_flags); /** * balance_dirty_pages_ratelimited - balance dirty memory state. * @mapping: address_space which was dirtied. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * Once we're over the dirty memory limit we decrease the ratelimiting * by a lot, to prevent individual processes from overshooting the limit * by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { balance_dirty_pages_ratelimited_flags(mapping, 0); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); /* * Similar to wb_dirty_limits, wb_bg_dirty_limits also calculates dirty * and thresh, but it's for background writeback. */ static void wb_bg_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; dtc->wb_bg_thresh = __wb_calc_thresh(dtc, dtc->bg_thresh); if (dtc->wb_bg_thresh < 2 * wb_stat_error()) dtc->wb_dirty = wb_stat_sum(wb, WB_RECLAIMABLE); else dtc->wb_dirty = wb_stat(wb, WB_RECLAIMABLE); } static bool domain_over_bg_thresh(struct dirty_throttle_control *dtc) { domain_dirty_avail(dtc, false); domain_dirty_limits(dtc); if (dtc->dirty > dtc->bg_thresh) return true; wb_bg_dirty_limits(dtc); if (dtc->wb_dirty > dtc->wb_bg_thresh) return true; return false; } /** * wb_over_bg_thresh - does @wb need to be written back? * @wb: bdi_writeback of interest * * Determines whether background writeback should keep writing @wb or it's * clean enough. * * Return: %true if writeback should continue. */ bool wb_over_bg_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) }; if (domain_over_bg_thresh(&gdtc)) return true; if (mdtc_valid(&mdtc)) return domain_over_bg_thresh(&mdtc); return false; } #ifdef CONFIG_SYSCTL /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ static int dirty_writeback_centisecs_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { unsigned int old_interval = dirty_writeback_interval; int ret; ret = proc_dointvec(table, write, buffer, length, ppos); /* * Writing 0 to dirty_writeback_interval will disable periodic writeback * and a different non-zero value will wakeup the writeback threads. * wb_wakeup_delayed() would be more appropriate, but it's a pain to * iterate over all bdis and wbs. * The reason we do this is to make the change take effect immediately. */ if (!ret && write && dirty_writeback_interval && dirty_writeback_interval != old_interval) wakeup_flusher_threads(WB_REASON_PERIODIC); return ret; } #endif void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = from_timer(backing_dev_info, t, laptop_mode_wb_timer); wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); } /* * We've spun up the disk and we're in laptop mode: schedule writeback * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ void laptop_io_completion(struct backing_dev_info *info) { mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* * We're in laptop mode and we've just synced. The sync's writes will have * caused another writeback to be scheduled by laptop_io_completion. * Nothing needs to be written back anymore, so we unschedule the writeback. */ void laptop_sync_completion(void) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) del_timer(&bdi->laptop_mode_wb_timer); rcu_read_unlock(); } /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory * thresholds. */ void writeback_set_ratelimit(void) { struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; global_dirty_limits(&background_thresh, &dirty_thresh); dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; } static int page_writeback_cpu_online(unsigned int cpu) { writeback_set_ratelimit(); return 0; } #ifdef CONFIG_SYSCTL /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; static struct ctl_table vm_page_writeback_sysctls[] = { { .procname = "dirty_background_ratio", .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, .proc_handler = dirty_background_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_background_bytes", .data = &dirty_background_bytes, .maxlen = sizeof(dirty_background_bytes), .mode = 0644, .proc_handler = dirty_background_bytes_handler, .extra1 = SYSCTL_LONG_ONE, }, { .procname = "dirty_ratio", .data = &vm_dirty_ratio, .maxlen = sizeof(vm_dirty_ratio), .mode = 0644, .proc_handler = dirty_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_bytes", .data = &vm_dirty_bytes, .maxlen = sizeof(vm_dirty_bytes), .mode = 0644, .proc_handler = dirty_bytes_handler, .extra1 = (void *)&dirty_bytes_min, }, { .procname = "dirty_writeback_centisecs", .data = &dirty_writeback_interval, .maxlen = sizeof(dirty_writeback_interval), .mode = 0644, .proc_handler = dirty_writeback_centisecs_handler, }, { .procname = "dirty_expire_centisecs", .data = &dirty_expire_interval, .maxlen = sizeof(dirty_expire_interval), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #ifdef CONFIG_HIGHMEM { .procname = "highmem_is_dirtyable", .data = &vm_highmem_is_dirtyable, .maxlen = sizeof(vm_highmem_is_dirtyable), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "laptop_mode", .data = &laptop_mode, .maxlen = sizeof(laptop_mode), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, }; #endif /* * Called early on to tune the page writeback dirty limits. * * We used to scale dirty pages according to how total memory * related to pages that could be allocated for buffers. * * However, that was when we used "dirty_ratio" to scale with * all memory, and we don't do that any more. "dirty_ratio" * is now applied to total non-HIGHPAGE memory, and as such we can't * get into the old insane situation any more where we had * large amounts of dirty pages compared to a small amount of * non-HIGHMEM memory. * * But we might still want to scale the dirty_ratio by how * much memory the box has.. */ void __init page_writeback_init(void) { BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online", page_writeback_cpu_online, NULL); cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL, page_writeback_cpu_online); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_page_writeback_sysctls); #endif } /** * tag_pages_for_writeback - tag pages to be written by writeback * @mapping: address space structure to write * @start: starting page index * @end: ending page index (inclusive) * * This function scans the page range from @start to @end (inclusive) and tags * all pages that have DIRTY tag set with a special TOWRITE tag. The caller * can then use the TOWRITE tag to identify pages eligible for writeback. * This mechanism is used to avoid livelocking of writeback by a process * steadily creating new dirty pages in the file (thus it is important for this * function to be quick so that it can tag pages faster than a dirtying process * can create them). */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); unsigned int tagged = 0; void *page; xas_lock_irq(&xas); xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); if (++tagged % XA_CHECK_SCHED) continue; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); static bool folio_prepare_writeback(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio) { /* * Folio truncated or invalidated. We can freely skip it then, * even for data integrity operations: the folio has disappeared * concurrently, so there could be no real expectation of this * data integrity operation even if there is now a new, dirty * folio at the same pagecache index. */ if (unlikely(folio->mapping != mapping)) return false; /* * Did somebody else write it for us? */ if (!folio_test_dirty(folio)) return false; if (folio_test_writeback(folio)) { if (wbc->sync_mode == WB_SYNC_NONE) return false; folio_wait_writeback(folio); } BUG_ON(folio_test_writeback(folio)); if (!folio_clear_dirty_for_io(folio)) return false; return true; } static xa_mark_t wbc_to_tag(struct writeback_control *wbc) { if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) return PAGECACHE_TAG_TOWRITE; return PAGECACHE_TAG_DIRTY; } static pgoff_t wbc_end(struct writeback_control *wbc) { if (wbc->range_cyclic) return -1; return wbc->range_end >> PAGE_SHIFT; } static struct folio *writeback_get_folio(struct address_space *mapping, struct writeback_control *wbc) { struct folio *folio; retry: folio = folio_batch_next(&wbc->fbatch); if (!folio) { folio_batch_release(&wbc->fbatch); cond_resched(); filemap_get_folios_tag(mapping, &wbc->index, wbc_end(wbc), wbc_to_tag(wbc), &wbc->fbatch); folio = folio_batch_next(&wbc->fbatch); if (!folio) return NULL; } folio_lock(folio); if (unlikely(!folio_prepare_writeback(mapping, wbc, folio))) { folio_unlock(folio); goto retry; } trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); return folio; } /** * writeback_iter - iterate folio of a mapping for writeback * @mapping: address space structure to write * @wbc: writeback context * @folio: previously iterated folio (%NULL to start) * @error: in-out pointer for writeback errors (see below) * * This function returns the next folio for the writeback operation described by * @wbc on @mapping and should be called in a while loop in the ->writepages * implementation. * * To start the writeback operation, %NULL is passed in the @folio argument, and * for every subsequent iteration the folio returned previously should be passed * back in. * * If there was an error in the per-folio writeback inside the writeback_iter() * loop, @error should be set to the error value. * * Once the writeback described in @wbc has finished, this function will return * %NULL and if there was an error in any iteration restore it to @error. * * Note: callers should not manually break out of the loop using break or goto * but must keep calling writeback_iter() until it returns %NULL. * * Return: the folio to write or %NULL if the loop is done. */ struct folio *writeback_iter(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio, int *error) { if (!folio) { folio_batch_init(&wbc->fbatch); wbc->saved_err = *error = 0; /* * For range cyclic writeback we remember where we stopped so * that we can continue where we stopped. * * For non-cyclic writeback we always start at the beginning of * the passed in range. */ if (wbc->range_cyclic) wbc->index = mapping->writeback_index; else wbc->index = wbc->range_start >> PAGE_SHIFT; /* * To avoid livelocks when other processes dirty new pages, we * first tag pages which should be written back and only then * start writing them. * * For data-integrity writeback we have to be careful so that we * do not miss some pages (e.g., because some other process has * cleared the TOWRITE tag we set). The rule we follow is that * TOWRITE tag can be cleared only by the process clearing the * DIRTY tag (and submitting the page for I/O). */ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, wbc->index, wbc_end(wbc)); } else { wbc->nr_to_write -= folio_nr_pages(folio); WARN_ON_ONCE(*error > 0); /* * For integrity writeback we have to keep going until we have * written all the folios we tagged for writeback above, even if * we run past wbc->nr_to_write or encounter errors. * We stash away the first error we encounter in wbc->saved_err * so that it can be retrieved when we're done. This is because * the file system may still have state to clear for each folio. * * For background writeback we exit as soon as we run past * wbc->nr_to_write or encounter the first error. */ if (wbc->sync_mode == WB_SYNC_ALL) { if (*error && !wbc->saved_err) wbc->saved_err = *error; } else { if (*error || wbc->nr_to_write <= 0) goto done; } } folio = writeback_get_folio(mapping, wbc); if (!folio) { /* * To avoid deadlocks between range_cyclic writeback and callers * that hold pages in PageWriteback to aggregate I/O until * the writeback iteration finishes, we do not loop back to the * start of the file. Doing so causes a page lock/page * writeback access order inversion - we should only ever lock * multiple pages in ascending page->index order, and looping * back to the start of the file violates that rule and causes * deadlocks. */ if (wbc->range_cyclic) mapping->writeback_index = 0; /* * Return the first error we encountered (if there was any) to * the caller. */ *error = wbc->saved_err; } return folio; done: if (wbc->range_cyclic) mapping->writeback_index = folio->index + folio_nr_pages(folio); folio_batch_release(&wbc->fbatch); return NULL; } EXPORT_SYMBOL_GPL(writeback_iter); /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * Return: %0 on success, negative error code otherwise * * Note: please use writeback_iter() instead. */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { struct folio *folio = NULL; int error; while ((folio = writeback_iter(mapping, wbc, folio, &error))) { error = writepage(folio, wbc, data); if (error == AOP_WRITEPAGE_ACTIVATE) { folio_unlock(folio); error = 0; } } return error; } EXPORT_SYMBOL(write_cache_pages); static int writeback_use_writepage(struct address_space *mapping, struct writeback_control *wbc) { struct folio *folio = NULL; struct blk_plug plug; int err; blk_start_plug(&plug); while ((folio = writeback_iter(mapping, wbc, folio, &err))) { err = mapping->a_ops->writepage(&folio->page, wbc); if (err == AOP_WRITEPAGE_ACTIVATE) { folio_unlock(folio); err = 0; } mapping_set_error(mapping, err); } blk_finish_plug(&plug); return err; } int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; struct bdi_writeback *wb; if (wbc->nr_to_write <= 0) return 0; wb = inode_to_wb_wbc(mapping->host, wbc); wb_bandwidth_estimate_start(wb); while (1) { if (mapping->a_ops->writepages) { ret = mapping->a_ops->writepages(mapping, wbc); } else if (mapping->a_ops->writepage) { ret = writeback_use_writepage(mapping, wbc); } else { /* deal with chardevs and other special files */ ret = 0; } if (ret != -ENOMEM || wbc->sync_mode != WB_SYNC_ALL) break; /* * Lacking an allocation context or the locality or writeback * state of any of the inode's pages, throttle based on * writeback activity on the local node. It's as good a * guess as any. */ reclaim_throttle(NODE_DATA(numa_node_id()), VMSCAN_THROTTLE_WRITEBACK); } /* * Usually few pages are written by now from those we've just submitted * but if there's constant writeback being submitted, this makes sure * writeback bandwidth is updated once in a while. */ if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) wb_update_bandwidth(wb); return ret; } /* * For address_spaces which do not use buffers nor write back. */ bool noop_dirty_folio(struct address_space *mapping, struct folio *folio) { if (!folio_test_dirty(folio)) return !folio_test_set_dirty(folio); return false; } EXPORT_SYMBOL(noop_dirty_folio); /* * Helper function for set_page_dirty family. * * Caller must hold folio_memcg_lock(). * * NOTE: This relies on being atomic wrt interrupts. */ static void folio_account_dirtied(struct folio *folio, struct address_space *mapping) { struct inode *inode = mapping->host; trace_writeback_dirty_folio(folio, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; long nr = folio_nr_pages(folio); inode_attach_wb(inode, folio); wb = inode_to_wb(inode); __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr); __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); __node_stat_mod_folio(folio, NR_DIRTIED, nr); wb_stat_mod(wb, WB_RECLAIMABLE, nr); wb_stat_mod(wb, WB_DIRTIED, nr); task_io_account_write(nr * PAGE_SIZE); current->nr_dirtied += nr; __this_cpu_add(bdp_ratelimits, nr); mem_cgroup_track_foreign_dirty(folio, wb); } } /* * Helper function for deaccounting dirty page without writeback. * * Caller must hold folio_memcg_lock(). */ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); task_io_account_cancelled_write(nr * PAGE_SIZE); } /* * Mark the folio dirty, and set it dirty in the page cache. * * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * * The caller must hold folio_memcg_lock(). It is the caller's * responsibility to prevent the folio from being truncated while * this function is in progress, although it may have been truncated * before this function is called. Most callers have the folio locked. * A few have the folio blocked from truncation through other means (e.g. * zap_vma_pages() has it mapped and is holding the page table lock). * When called from mark_buffer_dirty(), the filesystem should hold a * reference to the buffer_head that is being marked dirty, which causes * try_to_free_buffers() to fail. */ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, int warn) { unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); if (folio->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !folio_test_uptodate(folio)); folio_account_dirtied(folio, mapping); __xa_set_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_DIRTY); } xa_unlock_irqrestore(&mapping->i_pages, flags); } /** * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads. * @mapping: Address space this folio belongs to. * @folio: Folio to be marked as dirty. * * Filesystems which do not use buffer heads should call this function * from their dirty_folio address space operation. It ignores the * contents of folio_get_private(), so if the filesystem marks individual * blocks as dirty, the filesystem should handle that itself. * * This is also sometimes used by filesystems which use buffer_heads when * a single buffer is being dirtied: we want to set the folio dirty in * that case, but not all the buffers. This is a "bottom-up" dirtying, * whereas block_dirty_folio() is a "top-down" dirtying. * * The caller must ensure this doesn't race with truncation. Most will * simply hold the folio lock, but e.g. zap_pte_range() calls with the * folio mapped and the pte lock held, which also locks out truncation. */ bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) { folio_memcg_lock(folio); if (folio_test_set_dirty(folio)) { folio_memcg_unlock(folio); return false; } __folio_mark_dirty(folio, mapping, !folio_test_private(folio)); folio_memcg_unlock(folio); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return true; } EXPORT_SYMBOL(filemap_dirty_folio); /** * folio_redirty_for_writepage - Decline to write a dirty folio. * @wbc: The writeback control. * @folio: The folio. * * When a writepage implementation decides that it doesn't want to write * @folio for some reason, it should call this function, unlock @folio and * return 0. * * Return: True if we redirtied the folio. False if someone else dirtied * it first. */ bool folio_redirty_for_writepage(struct writeback_control *wbc, struct folio *folio) { struct address_space *mapping = folio->mapping; long nr = folio_nr_pages(folio); bool ret; wbc->pages_skipped += nr; ret = filemap_dirty_folio(mapping, folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied -= nr; node_stat_mod_folio(folio, NR_DIRTIED, -nr); wb_stat_mod(wb, WB_DIRTIED, -nr); unlocked_inode_to_wb_end(inode, &cookie); } return ret; } EXPORT_SYMBOL(folio_redirty_for_writepage); /** * folio_mark_dirty - Mark a folio as being modified. * @folio: The folio. * * The folio may not be truncated while this function is running. * Holding the folio lock is sufficient to prevent truncation, but some * callers cannot acquire a sleeping lock. These callers instead hold * the page table lock for a page table which contains at least one page * in this folio. Truncation will block on the page table lock as it * unmaps pages before removing the folio from its mapping. * * Return: True if the folio was newly dirtied, false if it was already dirty. */ bool folio_mark_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (likely(mapping)) { /* * readahead/folio_deactivate could remain * PG_readahead/PG_reclaim due to race with folio_end_writeback * About readahead, if the folio is written, the flags would be * reset. So no problem. * About folio_deactivate, if the folio is redirtied, * the flag will be reset. So no problem. but if the * folio is used by readahead it will confuse readahead * and make it restart the size rampup process. But it's * a trivial problem. */ if (folio_test_reclaim(folio)) folio_clear_reclaim(folio); return mapping->a_ops->dirty_folio(mapping, folio); } return noop_dirty_folio(mapping, folio); } EXPORT_SYMBOL(folio_mark_dirty); /* * set_page_dirty() is racy if the caller has no reference against * page->mapping->host, and if the page is unlocked. This is because another * CPU could truncate the page off the mapping and then free the mapping. * * Usually, the page _is_ locked, or the caller is a user-space process which * holds a reference on the inode by having an open file. * * In other cases, the page should be locked before running set_page_dirty(). */ int set_page_dirty_lock(struct page *page) { int ret; lock_page(page); ret = set_page_dirty(page); unlock_page(page); return ret; } EXPORT_SYMBOL(set_page_dirty_lock); /* * This cancels just the dirty bit on the kernel page itself, it does NOT * actually remove dirty bits on any mmap's that may be around. It also * leaves the page tagged dirty, so any sync activity will still find it on * the dirty lists, and in particular, clear_page_dirty_for_io() will still * look at the dirty bits in the VM. * * Doing this should *normally* only ever be done when a page is truncated, * and is not actually mapped anywhere at all. However, fs/buffer.c does * this when it notices that somebody has cleaned out all the buffers on a * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ void __folio_cancel_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; folio_memcg_lock(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) folio_account_cleaned(folio, wb); unlocked_inode_to_wb_end(inode, &cookie); folio_memcg_unlock(folio); } else { folio_clear_dirty(folio); } } EXPORT_SYMBOL(__folio_cancel_dirty); /* * Clear a folio's dirty flag, while caring for dirty memory accounting. * Returns true if the folio was previously dirty. * * This is for preparing to put the folio under writeout. We leave * the folio tagged as dirty in the xarray so that a concurrent * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk. * The ->writepage implementation will run either folio_start_writeback() * or folio_mark_dirty(), at which stage we bring the folio's dirty flag * and xarray dirty tag back into sync. * * This incoherency between the folio's dirty flag and xarray tag is * unfortunate, but it only exists while the folio is locked. */ bool folio_clear_dirty_for_io(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); bool ret = false; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. * * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to * mark the whole folio dirty if it was * dirty in a pagetable. Only to then * (c) clean the folio again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * * Note! Normally the "folio_mark_dirty(folio)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * * We basically use the folio "master dirty bit" * as a serialization point for all the different * threads doing their things. */ if (folio_mkclean(folio)) folio_mark_dirty(folio); /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the folio dirty * at this point. We do this by having them hold the * page lock while dirtying the folio, and folios are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); ret = true; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } return folio_test_clear_dirty(folio); } EXPORT_SYMBOL(folio_clear_dirty_for_io); static void wb_inode_writeback_start(struct bdi_writeback *wb) { atomic_inc(&wb->writeback_inodes); } static void wb_inode_writeback_end(struct bdi_writeback *wb) { unsigned long flags; atomic_dec(&wb->writeback_inodes); /* * Make sure estimate of writeback throughput gets updated after * writeback completed. We delay the update by BANDWIDTH_INTERVAL * (which is the interval other bandwidth updates use for batching) so * that if multiple inodes end writeback at a similar time, they get * batched into one bandwidth update. */ spin_lock_irqsave(&wb->work_lock, flags); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); spin_unlock_irqrestore(&wb->work_lock, flags); } bool __folio_end_writeback(struct folio *folio) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); bool ret; folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); __xa_clear_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, -nr); __wb_writeout_add(wb, nr); if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) wb_inode_writeback_end(wb); } if (mapping->host && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) sb_clear_inode_writeback(mapping->host); xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); node_stat_mod_folio(folio, NR_WRITTEN, nr); folio_memcg_unlock(folio); return ret; } void __folio_start_writeback(struct folio *folio, bool keep_write) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); int access_ret; VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; bool on_wblist; xas_lock_irqsave(&xas, flags); xas_load(&xas); folio_test_set_writeback(folio); on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, nr); if (!on_wblist) wb_inode_writeback_start(wb); } /* * We can come through here when swapping anonymous * folios, so we don't necessarily have an inode to * track for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); if (!folio_test_dirty(folio)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { folio_test_set_writeback(folio); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); folio_memcg_unlock(folio); access_ret = arch_make_folio_accessible(folio); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ VM_BUG_ON_FOLIO(access_ret != 0, folio); } EXPORT_SYMBOL(__folio_start_writeback); /** * folio_wait_writeback - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_writeback(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); folio_wait_bit(folio, PG_writeback); } } EXPORT_SYMBOL_GPL(folio_wait_writeback); /** * folio_wait_writeback_killable - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete or a fatal signal to arrive. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. * Return: 0 on success, -EINTR if we get a fatal signal while waiting. */ int folio_wait_writeback_killable(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); if (folio_wait_bit_killable(folio, PG_writeback)) return -EINTR; } return 0; } EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); /** * folio_wait_stable() - wait for writeback to finish, if necessary. * @folio: The folio to wait on. * * This function determines if the given folio is related to a backing * device that requires folio contents to be held stable during writeback. * If so, then it will wait for any pending writeback to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_stable(struct folio *folio) { if (mapping_stable_writes(folio_mapping(folio))) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_NF_TABLES_H #define _NET_NF_TABLES_H #include <asm/unaligned.h> #include <linux/list.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/nf_tables.h> #include <linux/u64_stats_sync.h> #include <linux/rhashtable.h> #include <net/netfilter/nf_flow_table.h> #include <net/netlink.h> #include <net/flow_offload.h> #include <net/netns/generic.h> #define NFT_MAX_HOOKS (NF_INET_INGRESS + 1) struct module; #define NFT_JUMP_STACK_SIZE 16 enum { NFT_PKTINFO_L4PROTO = (1 << 0), NFT_PKTINFO_INNER = (1 << 1), NFT_PKTINFO_INNER_FULL = (1 << 2), }; struct nft_pktinfo { struct sk_buff *skb; const struct nf_hook_state *state; u8 flags; u8 tprot; u16 fragoff; u16 thoff; u16 inneroff; }; static inline struct sock *nft_sk(const struct nft_pktinfo *pkt) { return pkt->state->sk; } static inline unsigned int nft_thoff(const struct nft_pktinfo *pkt) { return pkt->thoff; } static inline struct net *nft_net(const struct nft_pktinfo *pkt) { return pkt->state->net; } static inline unsigned int nft_hook(const struct nft_pktinfo *pkt) { return pkt->state->hook; } static inline u8 nft_pf(const struct nft_pktinfo *pkt) { return pkt->state->pf; } static inline const struct net_device *nft_in(const struct nft_pktinfo *pkt) { return pkt->state->in; } static inline const struct net_device *nft_out(const struct nft_pktinfo *pkt) { return pkt->state->out; } static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, struct sk_buff *skb, const struct nf_hook_state *state) { pkt->skb = skb; pkt->state = state; } static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt) { pkt->flags = 0; pkt->tprot = 0; pkt->thoff = 0; pkt->fragoff = 0; } /** * struct nft_verdict - nf_tables verdict * * @code: nf_tables/netfilter verdict code * @chain: destination chain for NFT_JUMP/NFT_GOTO */ struct nft_verdict { u32 code; struct nft_chain *chain; }; struct nft_data { union { u32 data[4]; struct nft_verdict verdict; }; } __attribute__((aligned(__alignof__(u64)))); #define NFT_REG32_NUM 20 /** * struct nft_regs - nf_tables register set * * @data: data registers * @verdict: verdict register * * The first four data registers alias to the verdict register. */ struct nft_regs { union { u32 data[NFT_REG32_NUM]; struct nft_verdict verdict; }; }; struct nft_regs_track { struct { const struct nft_expr *selector; const struct nft_expr *bitwise; u8 num_reg; } regs[NFT_REG32_NUM]; const struct nft_expr *cur; const struct nft_expr *last; }; /* Store/load an u8, u16 or u64 integer to/from the u32 data register. * * Note, when using concatenations, register allocation happens at 32-bit * level. So for store instruction, pad the rest part with zero to avoid * garbage values. */ static inline void nft_reg_store8(u32 *dreg, u8 val) { *dreg = 0; *(u8 *)dreg = val; } static inline u8 nft_reg_load8(const u32 *sreg) { return *(u8 *)sreg; } static inline void nft_reg_store16(u32 *dreg, u16 val) { *dreg = 0; *(u16 *)dreg = val; } static inline void nft_reg_store_be16(u32 *dreg, __be16 val) { nft_reg_store16(dreg, (__force __u16)val); } static inline u16 nft_reg_load16(const u32 *sreg) { return *(u16 *)sreg; } static inline __be16 nft_reg_load_be16(const u32 *sreg) { return (__force __be16)nft_reg_load16(sreg); } static inline __be32 nft_reg_load_be32(const u32 *sreg) { return *(__force __be32 *)sreg; } static inline void nft_reg_store64(u64 *dreg, u64 val) { put_unaligned(val, dreg); } static inline u64 nft_reg_load64(const u32 *sreg) { return get_unaligned((u64 *)sreg); } static inline void nft_data_copy(u32 *dst, const struct nft_data *src, unsigned int len) { if (len % NFT_REG32_SIZE) dst[len / NFT_REG32_SIZE] = 0; memcpy(dst, src, len); } /** * struct nft_ctx - nf_tables rule/set context * * @net: net namespace * @table: the table the chain is contained in * @chain: the chain the rule is contained in * @nla: netlink attributes * @portid: netlink portID of the original message * @seq: netlink sequence number * @flags: modifiers to new request * @family: protocol family * @level: depth of the chains * @report: notify via unicast netlink message */ struct nft_ctx { struct net *net; struct nft_table *table; struct nft_chain *chain; const struct nlattr * const *nla; u32 portid; u32 seq; u16 flags; u8 family; u8 level; bool report; }; enum nft_data_desc_flags { NFT_DATA_DESC_SETELEM = (1 << 0), }; struct nft_data_desc { enum nft_data_types type; unsigned int size; unsigned int len; unsigned int flags; }; int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data, struct nft_data_desc *desc, const struct nlattr *nla); void nft_data_hold(const struct nft_data *data, enum nft_data_types type); void nft_data_release(const struct nft_data *data, enum nft_data_types type); int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, enum nft_data_types type, unsigned int len); static inline enum nft_data_types nft_dreg_to_type(enum nft_registers reg) { return reg == NFT_REG_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE; } static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) { return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE; } int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len); int nft_parse_register_store(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *dreg, const struct nft_data *data, enum nft_data_types type, unsigned int len); /** * struct nft_userdata - user defined data associated with an object * * @len: length of the data * @data: content * * The presence of user data is indicated in an object specific fashion, * so a length of zero can't occur and the value "len" indicates data * of length len + 1. */ struct nft_userdata { u8 len; unsigned char data[]; }; /* placeholder structure for opaque set element backend representation. */ struct nft_elem_priv { }; /** * struct nft_set_elem - generic representation of set elements * * @key: element key * @key_end: closing element key * @data: element data * @priv: element private data and extensions */ struct nft_set_elem { union { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } key; union { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } key_end; union { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } data; struct nft_elem_priv *priv; }; static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) { return (void *)priv; } /** * enum nft_iter_type - nftables set iterator type * * @NFT_ITER_READ: read-only iteration over set elements * @NFT_ITER_UPDATE: iteration under mutex to update set element state */ enum nft_iter_type { NFT_ITER_UNSPEC, NFT_ITER_READ, NFT_ITER_UPDATE, }; struct nft_set; struct nft_set_iter { u8 genmask; enum nft_iter_type type:8; unsigned int count; unsigned int skip; int err; int (*fn)(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv); }; /** * struct nft_set_desc - description of set elements * * @ktype: key type * @klen: key length * @dtype: data type * @dlen: data length * @objtype: object type * @size: number of set elements * @policy: set policy * @gc_int: garbage collector interval * @timeout: element timeout * @field_len: length of each field in concatenation, bytes * @field_count: number of concatenated fields in element * @expr: set must support for expressions */ struct nft_set_desc { u32 ktype; unsigned int klen; u32 dtype; unsigned int dlen; u32 objtype; unsigned int size; u32 policy; u32 gc_int; u64 timeout; u8 field_len[NFT_REG32_COUNT]; u8 field_count; bool expr; }; /** * enum nft_set_class - performance class * * @NFT_SET_CLASS_O_1: constant, O(1) * @NFT_SET_CLASS_O_LOG_N: logarithmic, O(log N) * @NFT_SET_CLASS_O_N: linear, O(N) */ enum nft_set_class { NFT_SET_CLASS_O_1, NFT_SET_CLASS_O_LOG_N, NFT_SET_CLASS_O_N, }; /** * struct nft_set_estimate - estimation of memory and performance * characteristics * * @size: required memory * @lookup: lookup performance class * @space: memory class */ struct nft_set_estimate { u64 size; enum nft_set_class lookup; enum nft_set_class space; }; #define NFT_EXPR_MAXATTR 16 #define NFT_EXPR_SIZE(size) (sizeof(struct nft_expr) + \ ALIGN(size, __alignof__(struct nft_expr))) /** * struct nft_expr - nf_tables expression * * @ops: expression ops * @data: expression private data */ struct nft_expr { const struct nft_expr_ops *ops; unsigned char data[] __attribute__((aligned(__alignof__(u64)))); }; static inline void *nft_expr_priv(const struct nft_expr *expr) { return (void *)expr->data; } struct nft_expr_info; int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, struct nft_expr_info *info); int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src, gfp_t gfp); void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr, bool reset); bool nft_expr_reduce_bitwise(struct nft_regs_track *track, const struct nft_expr *expr); struct nft_set_ext; /** * struct nft_set_ops - nf_tables set operations * * @lookup: look up an element within the set * @update: update an element if exists, add it if doesn't exist * @delete: delete an element * @insert: insert new element into set * @activate: activate new element in the next generation * @deactivate: lookup for element and deactivate it in the next generation * @flush: deactivate element in the next generation * @remove: remove element from set * @walk: iterate over all set elements * @get: get set elements * @commit: commit set elements * @abort: abort set elements * @privsize: function to return size of set private data * @estimate: estimate the required memory size and the lookup complexity class * @init: initialize private data of new set instance * @destroy: destroy private data of set instance * @gc_init: initialize garbage collection * @elemsize: element private size * * Operations lookup, update and delete have simpler interfaces, are faster * and currently only used in the packet path. All the rest are slower, * control plane functions. */ struct nft_set_ops { bool (*lookup)(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext); bool (*update)(struct nft_set *set, const u32 *key, struct nft_elem_priv * (*new)(struct nft_set *, const struct nft_expr *, struct nft_regs *), const struct nft_expr *expr, struct nft_regs *regs, const struct nft_set_ext **ext); bool (*delete)(const struct nft_set *set, const u32 *key); int (*insert)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **priv); void (*activate)(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); struct nft_elem_priv * (*deactivate)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem); void (*flush)(const struct net *net, const struct nft_set *set, struct nft_elem_priv *priv); void (*remove)(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); void (*walk)(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter); struct nft_elem_priv * (*get)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags); void (*commit)(struct nft_set *set); void (*abort)(const struct nft_set *set); u64 (*privsize)(const struct nlattr * const nla[], const struct nft_set_desc *desc); bool (*estimate)(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est); int (*init)(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]); void (*destroy)(const struct nft_ctx *ctx, const struct nft_set *set); void (*gc_init)(const struct nft_set *set); unsigned int elemsize; }; /** * struct nft_set_type - nf_tables set type * * @ops: set ops for this type * @features: features supported by the implementation */ struct nft_set_type { const struct nft_set_ops ops; u32 features; }; #define to_set_type(o) container_of(o, struct nft_set_type, ops) struct nft_set_elem_expr { u8 size; unsigned char data[] __attribute__((aligned(__alignof__(struct nft_expr)))); }; #define nft_setelem_expr_at(__elem_expr, __offset) \ ((struct nft_expr *)&__elem_expr->data[__offset]) #define nft_setelem_expr_foreach(__expr, __elem_expr, __size) \ for (__expr = nft_setelem_expr_at(__elem_expr, 0), __size = 0; \ __size < (__elem_expr)->size; \ __size += (__expr)->ops->size, __expr = ((void *)(__expr)) + (__expr)->ops->size) #define NFT_SET_EXPR_MAX 2 /** * struct nft_set - nf_tables set instance * * @list: table set list node * @bindings: list of set bindings * @refs: internal refcounting for async set destruction * @table: table this set belongs to * @net: netnamespace this set belongs to * @name: name of the set * @handle: unique handle of the set * @ktype: key type (numeric type defined by userspace, not used in the kernel) * @dtype: data type (verdict or numeric type defined by userspace) * @objtype: object type (see NFT_OBJECT_* definitions) * @size: maximum set size * @field_len: length of each field in concatenation, bytes * @field_count: number of concatenated fields in element * @use: number of rules references to this set * @nelems: number of elements * @ndeact: number of deactivated elements queued for removal * @timeout: default timeout value in jiffies * @gc_int: garbage collection interval in msecs * @policy: set parameterization (see enum nft_set_policies) * @udlen: user data length * @udata: user data * @pending_update: list of pending update set element * @ops: set ops * @flags: set flags * @dead: set will be freed, never cleared * @genmask: generation mask * @klen: key length * @dlen: data length * @num_exprs: numbers of exprs * @exprs: stateful expression * @catchall_list: list of catch-all set element * @data: private set data */ struct nft_set { struct list_head list; struct list_head bindings; refcount_t refs; struct nft_table *table; possible_net_t net; char *name; u64 handle; u32 ktype; u32 dtype; u32 objtype; u32 size; u8 field_len[NFT_REG32_COUNT]; u8 field_count; u32 use; atomic_t nelems; u32 ndeact; u64 timeout; u32 gc_int; u16 policy; u16 udlen; unsigned char *udata; struct list_head pending_update; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; u16 flags:13, dead:1, genmask:2; u8 klen; u8 dlen; u8 num_exprs; struct nft_expr *exprs[NFT_SET_EXPR_MAX]; struct list_head catchall_list; unsigned char data[] __attribute__((aligned(__alignof__(u64)))); }; static inline bool nft_set_is_anonymous(const struct nft_set *set) { return set->flags & NFT_SET_ANONYMOUS; } static inline void *nft_set_priv(const struct nft_set *set) { return (void *)set->data; } static inline enum nft_data_types nft_set_datatype(const struct nft_set *set) { return set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE; } static inline bool nft_set_gc_is_pending(const struct nft_set *s) { return refcount_read(&s->refs) != 1; } static inline struct nft_set *nft_set_container_of(const void *priv) { return (void *)priv - offsetof(struct nft_set, data); } struct nft_set *nft_set_lookup_global(const struct net *net, const struct nft_table *table, const struct nlattr *nla_set_name, const struct nlattr *nla_set_id, u8 genmask); struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, const struct nft_set *set); static inline unsigned long nft_set_gc_interval(const struct nft_set *set) { u32 gc_int = READ_ONCE(set->gc_int); return gc_int ? msecs_to_jiffies(gc_int) : HZ; } /** * struct nft_set_binding - nf_tables set binding * * @list: set bindings list node * @chain: chain containing the rule bound to the set * @flags: set action flags * * A set binding contains all information necessary for validation * of new elements added to a bound set. */ struct nft_set_binding { struct list_head list; const struct nft_chain *chain; u32 flags; }; enum nft_trans_phase; void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set); void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase); int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); /** * enum nft_set_extensions - set extension type IDs * * @NFT_SET_EXT_KEY: element key * @NFT_SET_EXT_KEY_END: upper bound element key, for ranges * @NFT_SET_EXT_DATA: mapping data * @NFT_SET_EXT_FLAGS: element flags * @NFT_SET_EXT_TIMEOUT: element timeout * @NFT_SET_EXT_EXPIRATION: element expiration time * @NFT_SET_EXT_USERDATA: user data associated with the element * @NFT_SET_EXT_EXPRESSIONS: expressions assiciated with the element * @NFT_SET_EXT_OBJREF: stateful object reference associated with element * @NFT_SET_EXT_NUM: number of extension types */ enum nft_set_extensions { NFT_SET_EXT_KEY, NFT_SET_EXT_KEY_END, NFT_SET_EXT_DATA, NFT_SET_EXT_FLAGS, NFT_SET_EXT_TIMEOUT, NFT_SET_EXT_EXPIRATION, NFT_SET_EXT_USERDATA, NFT_SET_EXT_EXPRESSIONS, NFT_SET_EXT_OBJREF, NFT_SET_EXT_NUM }; /** * struct nft_set_ext_type - set extension type * * @len: fixed part length of the extension * @align: alignment requirements of the extension */ struct nft_set_ext_type { u8 len; u8 align; }; extern const struct nft_set_ext_type nft_set_ext_types[]; /** * struct nft_set_ext_tmpl - set extension template * * @len: length of extension area * @offset: offsets of individual extension types * @ext_len: length of the expected extension(used to sanity check) */ struct nft_set_ext_tmpl { u16 len; u8 offset[NFT_SET_EXT_NUM]; u8 ext_len[NFT_SET_EXT_NUM]; }; /** * struct nft_set_ext - set extensions * * @genmask: generation mask * @offset: offsets of individual extension types * @data: beginning of extension data */ struct nft_set_ext { u8 genmask; u8 offset[NFT_SET_EXT_NUM]; char data[]; }; static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) { memset(tmpl, 0, sizeof(*tmpl)); tmpl->len = sizeof(struct nft_set_ext); } static inline int nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id, unsigned int len) { tmpl->len = ALIGN(tmpl->len, nft_set_ext_types[id].align); if (tmpl->len > U8_MAX) return -EINVAL; tmpl->offset[id] = tmpl->len; tmpl->ext_len[id] = nft_set_ext_types[id].len + len; tmpl->len += tmpl->ext_len[id]; return 0; } static inline int nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id) { return nft_set_ext_add_length(tmpl, id, 0); } static inline void nft_set_ext_init(struct nft_set_ext *ext, const struct nft_set_ext_tmpl *tmpl) { memcpy(ext->offset, tmpl->offset, sizeof(ext->offset)); } static inline bool __nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) { return !!ext->offset[id]; } static inline bool nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) { return ext && __nft_set_ext_exists(ext, id); } static inline void *nft_set_ext(const struct nft_set_ext *ext, u8 id) { return (void *)ext + ext->offset[id]; } static inline struct nft_data *nft_set_ext_key(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_KEY); } static inline struct nft_data *nft_set_ext_key_end(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_KEY_END); } static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_DATA); } static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_FLAGS); } static inline u64 *nft_set_ext_timeout(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT); } static inline u64 *nft_set_ext_expiration(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION); } static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_USERDATA); } static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_EXPRESSIONS); } static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext, u64 tstamp) { return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) && time_after_eq64(tstamp, *nft_set_ext_expiration(ext)); } static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) { return __nft_set_elem_expired(ext, get_jiffies_64()); } static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, const struct nft_elem_priv *elem_priv) { return (void *)elem_priv + set->ops->elemsize; } static inline struct nft_object **nft_set_ext_obj(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_OBJREF); } struct nft_expr *nft_set_elem_expr_alloc(const struct nft_ctx *ctx, const struct nft_set *set, const struct nlattr *attr); struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *key_end, const u32 *data, u64 timeout, u64 expiration, gfp_t gfp); int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]); void nft_set_elem_destroy(const struct nft_set *set, const struct nft_elem_priv *elem_priv, bool destroy_expr); void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_elem_priv *elem_priv); struct nft_expr_ops; /** * struct nft_expr_type - nf_tables expression type * * @select_ops: function to select nft_expr_ops * @release_ops: release nft_expr_ops * @ops: default ops, used when no select_ops functions is present * @inner_ops: inner ops, used for inner packet operation * @list: used internally * @name: Identifier * @owner: module reference * @policy: netlink attribute policy * @maxattr: highest netlink attribute number * @family: address family for AF-specific types * @flags: expression type flags */ struct nft_expr_type { const struct nft_expr_ops *(*select_ops)(const struct nft_ctx *, const struct nlattr * const tb[]); void (*release_ops)(const struct nft_expr_ops *ops); const struct nft_expr_ops *ops; const struct nft_expr_ops *inner_ops; struct list_head list; const char *name; struct module *owner; const struct nla_policy *policy; unsigned int maxattr; u8 family; u8 flags; }; #define NFT_EXPR_STATEFUL 0x1 #define NFT_EXPR_GC 0x2 enum nft_trans_phase { NFT_TRANS_PREPARE, NFT_TRANS_PREPARE_ERROR, NFT_TRANS_ABORT, NFT_TRANS_COMMIT, NFT_TRANS_RELEASE }; struct nft_flow_rule; struct nft_offload_ctx; /** * struct nft_expr_ops - nf_tables expression operations * * @eval: Expression evaluation function * @clone: Expression clone function * @size: full expression size, including private data size * @init: initialization function * @activate: activate expression in the next generation * @deactivate: deactivate expression in next generation * @destroy: destruction function, called after synchronize_rcu * @destroy_clone: destruction clone function * @dump: function to dump parameters * @validate: validate expression, called during loop detection * @reduce: reduce expression * @gc: garbage collection expression * @offload: hardware offload expression * @offload_action: function to report true/false to allocate one slot or not in the flow * offload array * @offload_stats: function to synchronize hardware stats via updating the counter expression * @type: expression type * @data: extra data to attach to this expression operation */ struct nft_expr_ops { void (*eval)(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); int (*clone)(struct nft_expr *dst, const struct nft_expr *src, gfp_t gfp); unsigned int size; int (*init)(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); void (*activate)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*deactivate)(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase); void (*destroy)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*destroy_clone)(const struct nft_ctx *ctx, const struct nft_expr *expr); int (*dump)(struct sk_buff *skb, const struct nft_expr *expr, bool reset); int (*validate)(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data); bool (*reduce)(struct nft_regs_track *track, const struct nft_expr *expr); bool (*gc)(struct net *net, const struct nft_expr *expr); int (*offload)(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_expr *expr); bool (*offload_action)(const struct nft_expr *expr); void (*offload_stats)(struct nft_expr *expr, const struct flow_stats *stats); const struct nft_expr_type *type; void *data; }; /** * struct nft_rule - nf_tables rule * * @list: used internally * @handle: rule handle * @genmask: generation mask * @dlen: length of expression data * @udata: user data is appended to the rule * @data: expression data */ struct nft_rule { struct list_head list; u64 handle:42, genmask:2, dlen:12, udata:1; unsigned char data[] __attribute__((aligned(__alignof__(struct nft_expr)))); }; static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule) { return (struct nft_expr *)&rule->data[0]; } static inline struct nft_expr *nft_expr_next(const struct nft_expr *expr) { return ((void *)expr) + expr->ops->size; } static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule) { return (struct nft_expr *)&rule->data[rule->dlen]; } static inline bool nft_expr_more(const struct nft_rule *rule, const struct nft_expr *expr) { return expr != nft_expr_last(rule) && expr->ops; } static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) { return (void *)&rule->data[rule->dlen]; } void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule); void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, enum nft_trans_phase phase); void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule); static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_set_elem_expr *elem_expr; struct nft_expr *expr; u32 size; if (__nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) { elem_expr = nft_set_ext_expr(ext); nft_setelem_expr_foreach(expr, elem_expr, size) { expr->ops->eval(expr, regs, pkt); if (regs->verdict.code == NFT_BREAK) return; } } } /* * The last pointer isn't really necessary, but the compiler isn't able to * determine that the result of nft_expr_last() is always the same since it * can't assume that the dlen value wasn't changed within calls in the loop. */ #define nft_rule_for_each_expr(expr, last, rule) \ for ((expr) = nft_expr_first(rule), (last) = nft_expr_last(rule); \ (expr) != (last); \ (expr) = nft_expr_next(expr)) #define NFT_CHAIN_POLICY_UNSET U8_MAX struct nft_rule_dp { u64 is_last:1, dlen:12, handle:42; /* for tracing */ unsigned char data[] __attribute__((aligned(__alignof__(struct nft_expr)))); }; struct nft_rule_dp_last { struct nft_rule_dp end; /* end of nft_rule_blob marker */ struct rcu_head h; /* call_rcu head */ struct nft_rule_blob *blob; /* ptr to free via call_rcu */ const struct nft_chain *chain; /* for nftables tracing */ }; static inline const struct nft_rule_dp *nft_rule_next(const struct nft_rule_dp *rule) { return (void *)rule + sizeof(*rule) + rule->dlen; } struct nft_rule_blob { unsigned long size; unsigned char data[] __attribute__((aligned(__alignof__(struct nft_rule_dp)))); }; /** * struct nft_chain - nf_tables chain * * @blob_gen_0: rule blob pointer to the current generation * @blob_gen_1: rule blob pointer to the future generation * @rules: list of rules in the chain * @list: used internally * @rhlhead: used internally * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain * @flags: bitmask of enum NFTA_CHAIN_FLAGS * @bound: bind or not * @genmask: generation mask * @name: name of the chain * @udlen: user data length * @udata: user data in the chain * @blob_next: rule blob pointer to the next in the chain */ struct nft_chain { struct nft_rule_blob __rcu *blob_gen_0; struct nft_rule_blob __rcu *blob_gen_1; struct list_head rules; struct list_head list; struct rhlist_head rhlhead; struct nft_table *table; u64 handle; u32 use; u8 flags:5, bound:1, genmask:2; char *name; u16 udlen; u8 *udata; /* Only used during control plane commit phase: */ struct nft_rule_blob *blob_next; }; int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv); int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, NFT_CHAIN_T_ROUTE, NFT_CHAIN_T_NAT, NFT_CHAIN_T_MAX }; /** * struct nft_chain_type - nf_tables chain type info * * @name: name of the type * @type: numeric identifier * @family: address family * @owner: module owner * @hook_mask: mask of valid hooks * @hooks: array of hook functions * @ops_register: base chain register function * @ops_unregister: base chain unregister function */ struct nft_chain_type { const char *name; enum nft_chain_types type; int family; struct module *owner; unsigned int hook_mask; nf_hookfn *hooks[NFT_MAX_HOOKS]; int (*ops_register)(struct net *net, const struct nf_hook_ops *ops); void (*ops_unregister)(struct net *net, const struct nf_hook_ops *ops); }; int nft_chain_validate_dependency(const struct nft_chain *chain, enum nft_chain_types type); int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags); static inline bool nft_chain_binding(const struct nft_chain *chain) { return chain->flags & NFT_CHAIN_BINDING; } static inline bool nft_chain_is_bound(struct nft_chain *chain) { return (chain->flags & NFT_CHAIN_BINDING) && chain->bound; } int nft_chain_add(struct nft_table *table, struct nft_chain *chain); void nft_chain_del(struct nft_chain *chain); void nf_tables_chain_destroy(struct nft_chain *chain); struct nft_stats { u64 bytes; u64 pkts; struct u64_stats_sync syncp; }; struct nft_hook { struct list_head list; struct nf_hook_ops ops; struct rcu_head rcu; }; /** * struct nft_base_chain - nf_tables base chain * * @ops: netfilter hook ops * @hook_list: list of netfilter hooks (for NFPROTO_NETDEV family) * @type: chain type * @policy: default policy * @flags: indicate the base chain disabled or not * @stats: per-cpu chain stats * @chain: the chain * @flow_block: flow block (for hardware offload) */ struct nft_base_chain { struct nf_hook_ops ops; struct list_head hook_list; const struct nft_chain_type *type; u8 policy; u8 flags; struct nft_stats __percpu *stats; struct nft_chain chain; struct flow_block flow_block; }; static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain) { return container_of(chain, struct nft_base_chain, chain); } static inline bool nft_is_base_chain(const struct nft_chain *chain) { return chain->flags & NFT_CHAIN_BASE; } int __nft_release_basechain(struct nft_ctx *ctx); unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); static inline bool nft_use_inc(u32 *use) { if (*use == UINT_MAX) return false; (*use)++; return true; } static inline void nft_use_dec(u32 *use) { WARN_ON_ONCE((*use)-- == 0); } /* For error and abort path: restore use counter to previous state. */ static inline void nft_use_inc_restore(u32 *use) { WARN_ON_ONCE(!nft_use_inc(use)); } #define nft_use_dec_restore nft_use_dec /** * struct nft_table - nf_tables table * * @list: used internally * @chains_ht: chains in the table * @chains: same, for stable walks * @sets: sets in the table * @objects: stateful objects in the table * @flowtables: flow tables in the table * @hgenerator: handle generator state * @handle: table handle * @use: number of chain references to this table * @family:address family * @flags: table flag (see enum nft_table_flags) * @genmask: generation mask * @nlpid: netlink port ID * @name: name of the table * @udlen: length of the user data * @udata: user data * @validate_state: internal, set when transaction adds jumps */ struct nft_table { struct list_head list; struct rhltable chains_ht; struct list_head chains; struct list_head sets; struct list_head objects; struct list_head flowtables; u64 hgenerator; u64 handle; u32 use; u16 family:6, flags:8, genmask:2; u32 nlpid; char *name; u16 udlen; u8 *udata; u8 validate_state; }; static inline bool nft_table_has_owner(const struct nft_table *table) { return table->flags & NFT_TABLE_F_OWNER; } static inline bool nft_table_is_orphan(const struct nft_table *table) { return (table->flags & (NFT_TABLE_F_OWNER | NFT_TABLE_F_PERSIST)) == NFT_TABLE_F_PERSIST; } static inline bool nft_base_chain_netdev(int family, u32 hooknum) { return family == NFPROTO_NETDEV || (family == NFPROTO_INET && hooknum == NF_INET_INGRESS); } void nft_register_chain_type(const struct nft_chain_type *); void nft_unregister_chain_type(const struct nft_chain_type *); int nft_register_expr(struct nft_expr_type *); void nft_unregister_expr(struct nft_expr_type *); int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v); /** * struct nft_object_hash_key - key to lookup nft_object * * @name: name of the stateful object to look up * @table: table the object belongs to */ struct nft_object_hash_key { const char *name; const struct nft_table *table; }; /** * struct nft_object - nf_tables stateful object * * @list: table stateful object list node * @rhlhead: nft_objname_ht node * @key: keys that identify this object * @genmask: generation mask * @use: number of references to this stateful object * @handle: unique object handle * @udlen: length of user data * @udata: user data * @ops: object operations * @data: object data, layout depends on type */ struct nft_object { struct list_head list; struct rhlist_head rhlhead; struct nft_object_hash_key key; u32 genmask:2; u32 use; u64 handle; u16 udlen; u8 *udata; /* runtime data below here */ const struct nft_object_ops *ops ____cacheline_aligned; unsigned char data[] __attribute__((aligned(__alignof__(u64)))); }; static inline void *nft_obj_data(const struct nft_object *obj) { return (void *)obj->data; } #define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr)) struct nft_object *nft_obj_lookup(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask); void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, u16 flags, int family, int report, gfp_t gfp); /** * struct nft_object_type - stateful object type * * @select_ops: function to select nft_object_ops * @ops: default ops, used when no select_ops functions is present * @list: list node in list of object types * @type: stateful object numeric type * @owner: module owner * @maxattr: maximum netlink attribute * @family: address family for AF-specific object types * @policy: netlink attribute policy */ struct nft_object_type { const struct nft_object_ops *(*select_ops)(const struct nft_ctx *, const struct nlattr * const tb[]); const struct nft_object_ops *ops; struct list_head list; u32 type; unsigned int maxattr; u8 family; struct module *owner; const struct nla_policy *policy; }; /** * struct nft_object_ops - stateful object operations * * @eval: stateful object evaluation function * @size: stateful object size * @init: initialize object from netlink attributes * @destroy: release existing stateful object * @dump: netlink dump stateful object * @update: update stateful object * @type: pointer to object type */ struct nft_object_ops { void (*eval)(struct nft_object *obj, struct nft_regs *regs, const struct nft_pktinfo *pkt); unsigned int size; int (*init)(const struct nft_ctx *ctx, const struct nlattr *const tb[], struct nft_object *obj); void (*destroy)(const struct nft_ctx *ctx, struct nft_object *obj); int (*dump)(struct sk_buff *skb, struct nft_object *obj, bool reset); void (*update)(struct nft_object *obj, struct nft_object *newobj); const struct nft_object_type *type; }; int nft_register_obj(struct nft_object_type *obj_type); void nft_unregister_obj(struct nft_object_type *obj_type); #define NFT_NETDEVICE_MAX 256 /** * struct nft_flowtable - nf_tables flow table * * @list: flow table list node in table list * @table: the table the flow table is contained in * @name: name of this flow table * @hooknum: hook number * @ops_len: number of hooks in array * @genmask: generation mask * @use: number of references to this flow table * @handle: unique object handle * @hook_list: hook list for hooks per net_device in flowtables * @data: rhashtable and garbage collector */ struct nft_flowtable { struct list_head list; struct nft_table *table; char *name; int hooknum; int ops_len; u32 genmask:2; u32 use; u64 handle; /* runtime data below here */ struct list_head hook_list ____cacheline_aligned; struct nf_flowtable data; }; struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, const struct nlattr *nla, u8 genmask); void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, struct nft_flowtable *flowtable, enum nft_trans_phase phase); void nft_register_flowtable_type(struct nf_flowtable_type *type); void nft_unregister_flowtable_type(struct nf_flowtable_type *type); /** * struct nft_traceinfo - nft tracing information and state * * @trace: other struct members are initialised * @nf_trace: copy of skb->nf_trace before rule evaluation * @type: event type (enum nft_trace_types) * @skbid: hash of skb to be used as trace id * @packet_dumped: packet headers sent in a previous traceinfo message * @basechain: base chain currently processed */ struct nft_traceinfo { bool trace; bool nf_trace; bool packet_dumped; enum nft_trace_types type:8; u32 skbid; const struct nft_base_chain *basechain; }; void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, const struct nft_chain *basechain); void nft_trace_notify(const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, const struct nft_rule_dp *rule, struct nft_traceinfo *info); #define MODULE_ALIAS_NFT_CHAIN(family, name) \ MODULE_ALIAS("nft-chain-" __stringify(family) "-" name) #define MODULE_ALIAS_NFT_AF_EXPR(family, name) \ MODULE_ALIAS("nft-expr-" __stringify(family) "-" name) #define MODULE_ALIAS_NFT_EXPR(name) \ MODULE_ALIAS("nft-expr-" name) #define MODULE_ALIAS_NFT_OBJ(type) \ MODULE_ALIAS("nft-obj-" __stringify(type)) #if IS_ENABLED(CONFIG_NF_TABLES) /* * The gencursor defines two generations, the currently active and the * next one. Objects contain a bitmask of 2 bits specifying the generations * they're active in. A set bit means they're inactive in the generation * represented by that bit. * * New objects start out as inactive in the current and active in the * next generation. When committing the ruleset the bitmask is cleared, * meaning they're active in all generations. When removing an object, * it is set inactive in the next generation. After committing the ruleset, * the objects are removed. */ static inline unsigned int nft_gencursor_next(const struct net *net) { return net->nft.gencursor + 1 == 1 ? 1 : 0; } static inline u8 nft_genmask_next(const struct net *net) { return 1 << nft_gencursor_next(net); } static inline u8 nft_genmask_cur(const struct net *net) { /* Use READ_ONCE() to prevent refetching the value for atomicity */ return 1 << READ_ONCE(net->nft.gencursor); } #define NFT_GENMASK_ANY ((1 << 0) | (1 << 1)) /* * Generic transaction helpers */ /* Check if this object is currently active. */ #define nft_is_active(__net, __obj) \ (((__obj)->genmask & nft_genmask_cur(__net)) == 0) /* Check if this object is active in the next generation. */ #define nft_is_active_next(__net, __obj) \ (((__obj)->genmask & nft_genmask_next(__net)) == 0) /* This object becomes active in the next generation. */ #define nft_activate_next(__net, __obj) \ (__obj)->genmask = nft_genmask_cur(__net) /* This object becomes inactive in the next generation. */ #define nft_deactivate_next(__net, __obj) \ (__obj)->genmask = nft_genmask_next(__net) /* After committing the ruleset, clear the stale generation bit. */ #define nft_clear(__net, __obj) \ (__obj)->genmask &= ~nft_genmask_next(__net) #define nft_active_genmask(__obj, __genmask) \ !((__obj)->genmask & __genmask) /* * Set element transaction helpers */ static inline bool nft_set_elem_active(const struct nft_set_ext *ext, u8 genmask) { return !(ext->genmask & genmask); } static inline void nft_set_elem_change_active(const struct net *net, const struct nft_set *set, struct nft_set_ext *ext) { ext->genmask ^= nft_genmask_next(net); } #endif /* IS_ENABLED(CONFIG_NF_TABLES) */ #define NFT_SET_ELEM_DEAD_MASK (1 << 2) #if defined(__LITTLE_ENDIAN_BITFIELD) #define NFT_SET_ELEM_DEAD_BIT 2 #elif defined(__BIG_ENDIAN_BITFIELD) #define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) #else #error #endif static inline void nft_set_elem_dead(struct nft_set_ext *ext) { unsigned long *word = (unsigned long *)ext; BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); set_bit(NFT_SET_ELEM_DEAD_BIT, word); } static inline int nft_set_elem_is_dead(const struct nft_set_ext *ext) { unsigned long *word = (unsigned long *)ext; BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); return test_bit(NFT_SET_ELEM_DEAD_BIT, word); } /** * struct nft_trans - nf_tables object update in transaction * * @list: used internally * @net: struct net * @table: struct nft_table the object resides in * @msg_type: message type * @seq: netlink sequence number * @flags: modifiers to new request * @report: notify via unicast netlink message * @put_net: net needs to be put * * This is the information common to all objects in the transaction, * this must always be the first member of derived sub-types. */ struct nft_trans { struct list_head list; struct net *net; struct nft_table *table; int msg_type; u32 seq; u16 flags; u8 report:1; u8 put_net:1; }; /** * struct nft_trans_binding - nf_tables object with binding support in transaction * @nft_trans: base structure, MUST be first member * @binding_list: list of objects with possible bindings * * This is the base type used by objects that can be bound to a chain. */ struct nft_trans_binding { struct nft_trans nft_trans; struct list_head binding_list; }; struct nft_trans_rule { struct nft_trans nft_trans; struct nft_rule *rule; struct nft_chain *chain; struct nft_flow_rule *flow; u32 rule_id; bool bound; }; #define nft_trans_container_rule(trans) \ container_of(trans, struct nft_trans_rule, nft_trans) #define nft_trans_rule(trans) \ nft_trans_container_rule(trans)->rule #define nft_trans_flow_rule(trans) \ nft_trans_container_rule(trans)->flow #define nft_trans_rule_id(trans) \ nft_trans_container_rule(trans)->rule_id #define nft_trans_rule_bound(trans) \ nft_trans_container_rule(trans)->bound #define nft_trans_rule_chain(trans) \ nft_trans_container_rule(trans)->chain struct nft_trans_set { struct nft_trans_binding nft_trans_binding; struct nft_set *set; u32 set_id; u32 gc_int; u64 timeout; bool update; bool bound; u32 size; }; #define nft_trans_container_set(t) \ container_of(t, struct nft_trans_set, nft_trans_binding.nft_trans) #define nft_trans_set(trans) \ nft_trans_container_set(trans)->set #define nft_trans_set_id(trans) \ nft_trans_container_set(trans)->set_id #define nft_trans_set_bound(trans) \ nft_trans_container_set(trans)->bound #define nft_trans_set_update(trans) \ nft_trans_container_set(trans)->update #define nft_trans_set_timeout(trans) \ nft_trans_container_set(trans)->timeout #define nft_trans_set_gc_int(trans) \ nft_trans_container_set(trans)->gc_int #define nft_trans_set_size(trans) \ nft_trans_container_set(trans)->size struct nft_trans_chain { struct nft_trans_binding nft_trans_binding; struct nft_chain *chain; char *name; struct nft_stats __percpu *stats; u8 policy; bool update; bool bound; u32 chain_id; struct nft_base_chain *basechain; struct list_head hook_list; }; #define nft_trans_container_chain(t) \ container_of(t, struct nft_trans_chain, nft_trans_binding.nft_trans) #define nft_trans_chain(trans) \ nft_trans_container_chain(trans)->chain #define nft_trans_chain_update(trans) \ nft_trans_container_chain(trans)->update #define nft_trans_chain_name(trans) \ nft_trans_container_chain(trans)->name #define nft_trans_chain_stats(trans) \ nft_trans_container_chain(trans)->stats #define nft_trans_chain_policy(trans) \ nft_trans_container_chain(trans)->policy #define nft_trans_chain_bound(trans) \ nft_trans_container_chain(trans)->bound #define nft_trans_chain_id(trans) \ nft_trans_container_chain(trans)->chain_id #define nft_trans_basechain(trans) \ nft_trans_container_chain(trans)->basechain #define nft_trans_chain_hooks(trans) \ nft_trans_container_chain(trans)->hook_list struct nft_trans_table { struct nft_trans nft_trans; bool update; }; #define nft_trans_container_table(trans) \ container_of(trans, struct nft_trans_table, nft_trans) #define nft_trans_table_update(trans) \ nft_trans_container_table(trans)->update struct nft_trans_elem { struct nft_trans nft_trans; struct nft_set *set; struct nft_elem_priv *elem_priv; bool bound; }; #define nft_trans_container_elem(t) \ container_of(t, struct nft_trans_elem, nft_trans) #define nft_trans_elem_set(trans) \ nft_trans_container_elem(trans)->set #define nft_trans_elem_priv(trans) \ nft_trans_container_elem(trans)->elem_priv #define nft_trans_elem_set_bound(trans) \ nft_trans_container_elem(trans)->bound struct nft_trans_obj { struct nft_trans nft_trans; struct nft_object *obj; struct nft_object *newobj; bool update; }; #define nft_trans_container_obj(t) \ container_of(t, struct nft_trans_obj, nft_trans) #define nft_trans_obj(trans) \ nft_trans_container_obj(trans)->obj #define nft_trans_obj_newobj(trans) \ nft_trans_container_obj(trans)->newobj #define nft_trans_obj_update(trans) \ nft_trans_container_obj(trans)->update struct nft_trans_flowtable { struct nft_trans nft_trans; struct nft_flowtable *flowtable; struct list_head hook_list; u32 flags; bool update; }; #define nft_trans_container_flowtable(t) \ container_of(t, struct nft_trans_flowtable, nft_trans) #define nft_trans_flowtable(trans) \ nft_trans_container_flowtable(trans)->flowtable #define nft_trans_flowtable_update(trans) \ nft_trans_container_flowtable(trans)->update #define nft_trans_flowtable_hooks(trans) \ nft_trans_container_flowtable(trans)->hook_list #define nft_trans_flowtable_flags(trans) \ nft_trans_container_flowtable(trans)->flags #define NFT_TRANS_GC_BATCHCOUNT 256 struct nft_trans_gc { struct list_head list; struct net *net; struct nft_set *set; u32 seq; u16 count; struct nft_elem_priv *priv[NFT_TRANS_GC_BATCHCOUNT]; struct rcu_head rcu; }; static inline void nft_ctx_update(struct nft_ctx *ctx, const struct nft_trans *trans) { switch (trans->msg_type) { case NFT_MSG_NEWRULE: case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: ctx->chain = nft_trans_rule_chain(trans); break; case NFT_MSG_NEWCHAIN: case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: ctx->chain = nft_trans_chain(trans); break; default: ctx->chain = NULL; break; } ctx->net = trans->net; ctx->table = trans->table; ctx->family = trans->table->family; ctx->report = trans->report; ctx->flags = trans->flags; ctx->seq = trans->seq; } struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, unsigned int gc_seq, gfp_t gfp); void nft_trans_gc_destroy(struct nft_trans_gc *trans); struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp); void nft_trans_gc_queue_async_done(struct nft_trans_gc *gc); struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp); void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans); void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv); struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, unsigned int gc_seq); struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc); void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv); int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); void __init nft_chain_route_init(void); void nft_chain_route_fini(void); void nf_tables_trans_destroy_flush_work(void); int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result); __be64 nf_jiffies64_to_msecs(u64 input); #ifdef CONFIG_MODULES __printf(2, 3) int nft_request_module(struct net *net, const char *fmt, ...); #else static inline int nft_request_module(struct net *net, const char *fmt, ...) { return -ENOENT; } #endif struct nftables_pernet { struct list_head tables; struct list_head commit_list; struct list_head binding_list; struct list_head module_list; struct list_head notify_list; struct mutex commit_mutex; u64 table_handle; u64 tstamp; unsigned int base_seq; unsigned int gc_seq; u8 validate_state; }; extern unsigned int nf_tables_net_id; static inline struct nftables_pernet *nft_pernet(const struct net *net) { return net_generic(net, nf_tables_net_id); } static inline u64 nft_net_tstamp(const struct net *net) { return nft_pernet(net)->tstamp; } #define __NFT_REDUCE_READONLY 1UL #define NFT_REDUCE_READONLY (void *)__NFT_REDUCE_READONLY static inline bool nft_reduce_is_readonly(const struct nft_expr *expr) { return expr->ops->reduce == NFT_REDUCE_READONLY; } void nft_reg_track_update(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg, u8 len); void nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg, u8 len); void __nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg); static inline bool nft_reg_track_cmp(struct nft_regs_track *track, const struct nft_expr *expr, u8 dreg) { return track->regs[dreg].selector && track->regs[dreg].selector->ops == expr->ops && track->regs[dreg].num_reg == 0; } #endif /* _NET_NF_TABLES_H */ |
| 187 187 187 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com> * Copyright (C) 2002 Andi Kleen * * This handles calls from both 32bit and 64bit mode. * * Lock order: * context.ldt_usr_sem * mmap_lock * context.lock */ #include <linux/errno.h> #include <linux/gfp.h> #include <linux/sched.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> #include <asm/ldt.h> #include <asm/tlb.h> #include <asm/desc.h> #include <asm/mmu_context.h> #include <asm/pgtable_areas.h> #include <xen/xen.h> /* This is a multiple of PAGE_SIZE. */ #define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) static inline void *ldt_slot_va(int slot) { return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); } void load_mm_ldt(struct mm_struct *mm) { struct ldt_struct *ldt; /* READ_ONCE synchronizes with smp_store_release */ ldt = READ_ONCE(mm->context.ldt); /* * Any change to mm->context.ldt is followed by an IPI to all * CPUs with the mm active. The LDT will not be freed until * after the IPI is handled by all such CPUs. This means that * if the ldt_struct changes before we return, the values we see * will be safe, and the new values will be loaded before we run * any user code. * * NB: don't try to convert this to use RCU without extreme care. * We would still need IRQs off, because we don't want to change * the local LDT after an IPI loaded a newer value than the one * that we can see. */ if (unlikely(ldt)) { if (static_cpu_has(X86_FEATURE_PTI)) { if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) { /* * Whoops -- either the new LDT isn't mapped * (if slot == -1) or is mapped into a bogus * slot (if slot > 1). */ clear_LDT(); return; } /* * If page table isolation is enabled, ldt->entries * will not be mapped in the userspace pagetables. * Tell the CPU to access the LDT through the alias * at ldt_slot_va(ldt->slot). */ set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries); } else { set_ldt(ldt->entries, ldt->nr_entries); } } else { clear_LDT(); } } void switch_ldt(struct mm_struct *prev, struct mm_struct *next) { /* * Load the LDT if either the old or new mm had an LDT. * * An mm will never go from having an LDT to not having an LDT. Two * mms never share an LDT, so we don't gain anything by checking to * see whether the LDT changed. There's also no guarantee that * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL, * then prev->context.ldt will also be non-NULL. * * If we really cared, we could optimize the case where prev == next * and we're exiting lazy mode. Most of the time, if this happens, * we don't actually need to reload LDTR, but modify_ldt() is mostly * used by legacy code and emulators where we don't need this level of * performance. * * This uses | instead of || because it generates better code. */ if (unlikely((unsigned long)prev->context.ldt | (unsigned long)next->context.ldt)) load_mm_ldt(next); DEBUG_LOCKS_WARN_ON(preemptible()); } static void refresh_ldt_segments(void) { #ifdef CONFIG_X86_64 unsigned short sel; /* * Make sure that the cached DS and ES descriptors match the updated * LDT. */ savesegment(ds, sel); if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) loadsegment(ds, sel); savesegment(es, sel); if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) loadsegment(es, sel); #endif } /* context.lock is held by the task which issued the smp function call */ static void flush_ldt(void *__mm) { struct mm_struct *mm = __mm; if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm) return; load_mm_ldt(mm); refresh_ldt_segments(); } /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) { struct ldt_struct *new_ldt; unsigned int alloc_size; if (num_entries > LDT_ENTRIES) return NULL; new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL_ACCOUNT); if (!new_ldt) return NULL; BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); alloc_size = num_entries * LDT_ENTRY_SIZE; /* * Xen is very picky: it requires a page-aligned LDT that has no * trailing nonzero bytes in any page that contains LDT descriptors. * Keep it simple: zero the whole allocation and never allocate less * than PAGE_SIZE. */ if (alloc_size > PAGE_SIZE) new_ldt->entries = __vmalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); else new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!new_ldt->entries) { kfree(new_ldt); return NULL; } /* The new LDT isn't aliased for PTI yet. */ new_ldt->slot = -1; new_ldt->nr_entries = num_entries; return new_ldt; } #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void do_sanity_check(struct mm_struct *mm, bool had_kernel_mapping, bool had_user_mapping) { if (mm->context.ldt) { /* * We already had an LDT. The top-level entry should already * have been allocated and synchronized with the usermode * tables. */ WARN_ON(!had_kernel_mapping); if (boot_cpu_has(X86_FEATURE_PTI)) WARN_ON(!had_user_mapping); } else { /* * This is the first time we're mapping an LDT for this process. * Sync the pgd to the usermode tables. */ WARN_ON(had_kernel_mapping); if (boot_cpu_has(X86_FEATURE_PTI)) WARN_ON(had_user_mapping); } } #ifdef CONFIG_X86_PAE static pmd_t *pgd_to_pmd_walk(pgd_t *pgd, unsigned long va) { p4d_t *p4d; pud_t *pud; if (pgd->pgd == 0) return NULL; p4d = p4d_offset(pgd, va); if (p4d_none(*p4d)) return NULL; pud = pud_offset(p4d, va); if (pud_none(*pud)) return NULL; return pmd_offset(pud, va); } static void map_ldt_struct_to_user(struct mm_struct *mm) { pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR); pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); pmd_t *k_pmd, *u_pmd; k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR); u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR); if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt) set_pmd(u_pmd, *k_pmd); } static void sanity_check_ldt_mapping(struct mm_struct *mm) { pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR); pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); bool had_kernel, had_user; pmd_t *k_pmd, *u_pmd; k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR); u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR); had_kernel = (k_pmd->pmd != 0); had_user = (u_pmd->pmd != 0); do_sanity_check(mm, had_kernel, had_user); } #else /* !CONFIG_X86_PAE */ static void map_ldt_struct_to_user(struct mm_struct *mm) { pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR); if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt) set_pgd(kernel_to_user_pgdp(pgd), *pgd); } static void sanity_check_ldt_mapping(struct mm_struct *mm) { pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR); bool had_kernel = (pgd->pgd != 0); bool had_user = (kernel_to_user_pgdp(pgd)->pgd != 0); do_sanity_check(mm, had_kernel, had_user); } #endif /* CONFIG_X86_PAE */ /* * If PTI is enabled, this maps the LDT into the kernelmode and * usermode tables for the given mm. */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) { unsigned long va; bool is_vmalloc; spinlock_t *ptl; int i, nr_pages; if (!boot_cpu_has(X86_FEATURE_PTI)) return 0; /* * Any given ldt_struct should have map_ldt_struct() called at most * once. */ WARN_ON(ldt->slot != -1); /* Check if the current mappings are sane */ sanity_check_ldt_mapping(mm); is_vmalloc = is_vmalloc_addr(ldt->entries); nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); for (i = 0; i < nr_pages; i++) { unsigned long offset = i << PAGE_SHIFT; const void *src = (char *)ldt->entries + offset; unsigned long pfn; pgprot_t pte_prot; pte_t pte, *ptep; va = (unsigned long)ldt_slot_va(slot) + offset; pfn = is_vmalloc ? vmalloc_to_pfn(src) : page_to_pfn(virt_to_page(src)); /* * Treat the PTI LDT range as a *userspace* range. * get_locked_pte() will allocate all needed pagetables * and account for them in this mm. */ ptep = get_locked_pte(mm, va, &ptl); if (!ptep) return -ENOMEM; /* * Map it RO so the easy to find address is not a primary * target via some kernel interface which misses a * permission check. */ pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL); /* Filter out unsuppored __PAGE_KERNEL* bits: */ pgprot_val(pte_prot) &= __supported_pte_mask; pte = pfn_pte(pfn, pte_prot); set_pte_at(mm, va, ptep, pte); pte_unmap_unlock(ptep, ptl); } /* Propagate LDT mapping to the user page-table */ map_ldt_struct_to_user(mm); ldt->slot = slot; return 0; } static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) { unsigned long va; int i, nr_pages; if (!ldt) return; /* LDT map/unmap is only required for PTI */ if (!boot_cpu_has(X86_FEATURE_PTI)) return; nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); for (i = 0; i < nr_pages; i++) { unsigned long offset = i << PAGE_SHIFT; spinlock_t *ptl; pte_t *ptep; va = (unsigned long)ldt_slot_va(ldt->slot) + offset; ptep = get_locked_pte(mm, va, &ptl); if (!WARN_ON_ONCE(!ptep)) { pte_clear(mm, va, ptep); pte_unmap_unlock(ptep, ptl); } } va = (unsigned long)ldt_slot_va(ldt->slot); flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false); } #else /* !CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) { return 0; } static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) { } #endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static void free_ldt_pgtables(struct mm_struct *mm) { #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION struct mmu_gather tlb; unsigned long start = LDT_BASE_ADDR; unsigned long end = LDT_END_ADDR; if (!boot_cpu_has(X86_FEATURE_PTI)) return; /* * Although free_pgd_range() is intended for freeing user * page-tables, it also works out for kernel mappings on x86. * We use tlb_gather_mmu_fullmm() to avoid confusing the * range-tracking logic in __tlb_adjust_range(). */ tlb_gather_mmu_fullmm(&tlb, mm); free_pgd_range(&tlb, start, end, start, end); tlb_finish_mmu(&tlb); #endif } /* After calling this, the LDT is immutable. */ static void finalize_ldt_struct(struct ldt_struct *ldt) { paravirt_alloc_ldt(ldt->entries, ldt->nr_entries); } static void install_ldt(struct mm_struct *mm, struct ldt_struct *ldt) { mutex_lock(&mm->context.lock); /* Synchronizes with READ_ONCE in load_mm_ldt. */ smp_store_release(&mm->context.ldt, ldt); /* Activate the LDT for all CPUs using currents mm. */ on_each_cpu_mask(mm_cpumask(mm), flush_ldt, mm, true); mutex_unlock(&mm->context.lock); } static void free_ldt_struct(struct ldt_struct *ldt) { if (likely(!ldt)) return; paravirt_free_ldt(ldt->entries, ldt->nr_entries); if (ldt->nr_entries * LDT_ENTRY_SIZE > PAGE_SIZE) vfree_atomic(ldt->entries); else free_page((unsigned long)ldt->entries); kfree(ldt); } /* * Called on fork from arch_dup_mmap(). Just copy the current LDT state, * the new task is not running, so nothing can be installed. */ int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm) { struct ldt_struct *new_ldt; int retval = 0; if (!old_mm) return 0; mutex_lock(&old_mm->context.lock); if (!old_mm->context.ldt) goto out_unlock; new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries); if (!new_ldt) { retval = -ENOMEM; goto out_unlock; } memcpy(new_ldt->entries, old_mm->context.ldt->entries, new_ldt->nr_entries * LDT_ENTRY_SIZE); finalize_ldt_struct(new_ldt); retval = map_ldt_struct(mm, new_ldt, 0); if (retval) { free_ldt_pgtables(mm); free_ldt_struct(new_ldt); goto out_unlock; } mm->context.ldt = new_ldt; out_unlock: mutex_unlock(&old_mm->context.lock); return retval; } /* * No need to lock the MM as we are the last user * * 64bit: Don't touch the LDT register - we're already in the next thread. */ void destroy_context_ldt(struct mm_struct *mm) { free_ldt_struct(mm->context.ldt); mm->context.ldt = NULL; } void ldt_arch_exit_mmap(struct mm_struct *mm) { free_ldt_pgtables(mm); } static int read_ldt(void __user *ptr, unsigned long bytecount) { struct mm_struct *mm = current->mm; unsigned long entries_size; int retval; down_read(&mm->context.ldt_usr_sem); if (!mm->context.ldt) { retval = 0; goto out_unlock; } if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; entries_size = mm->context.ldt->nr_entries * LDT_ENTRY_SIZE; if (entries_size > bytecount) entries_size = bytecount; if (copy_to_user(ptr, mm->context.ldt->entries, entries_size)) { retval = -EFAULT; goto out_unlock; } if (entries_size != bytecount) { /* Zero-fill the rest and pretend we read bytecount bytes. */ if (clear_user(ptr + entries_size, bytecount - entries_size)) { retval = -EFAULT; goto out_unlock; } } retval = bytecount; out_unlock: up_read(&mm->context.ldt_usr_sem); return retval; } static int read_default_ldt(void __user *ptr, unsigned long bytecount) { /* CHECKME: Can we use _one_ random number ? */ #ifdef CONFIG_X86_32 unsigned long size = 5 * sizeof(struct desc_struct); #else unsigned long size = 128; #endif if (bytecount > size) bytecount = size; if (clear_user(ptr, bytecount)) return -EFAULT; return bytecount; } static bool allow_16bit_segments(void) { if (!IS_ENABLED(CONFIG_X86_16BIT)) return false; #ifdef CONFIG_XEN_PV /* * Xen PV does not implement ESPFIX64, which means that 16-bit * segments will not work correctly. Until either Xen PV implements * ESPFIX64 and can signal this fact to the guest or unless someone * provides compelling evidence that allowing broken 16-bit segments * is worthwhile, disallow 16-bit segments under Xen PV. */ if (xen_pv_domain()) { pr_info_once("Warning: 16-bit segments do not work correctly in a Xen PV guest\n"); return false; } #endif return true; } static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) { struct mm_struct *mm = current->mm; struct ldt_struct *new_ldt, *old_ldt; unsigned int old_nr_entries, new_nr_entries; struct user_desc ldt_info; struct desc_struct ldt; int error; error = -EINVAL; if (bytecount != sizeof(ldt_info)) goto out; error = -EFAULT; if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info))) goto out; error = -EINVAL; if (ldt_info.entry_number >= LDT_ENTRIES) goto out; if (ldt_info.contents == 3) { if (oldmode) goto out; if (ldt_info.seg_not_present == 0) goto out; } if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) || LDT_empty(&ldt_info)) { /* The user wants to clear the entry. */ memset(&ldt, 0, sizeof(ldt)); } else { if (!ldt_info.seg_32bit && !allow_16bit_segments()) { error = -EINVAL; goto out; } fill_ldt(&ldt, &ldt_info); if (oldmode) ldt.avl = 0; } if (down_write_killable(&mm->context.ldt_usr_sem)) return -EINTR; old_ldt = mm->context.ldt; old_nr_entries = old_ldt ? old_ldt->nr_entries : 0; new_nr_entries = max(ldt_info.entry_number + 1, old_nr_entries); error = -ENOMEM; new_ldt = alloc_ldt_struct(new_nr_entries); if (!new_ldt) goto out_unlock; if (old_ldt) memcpy(new_ldt->entries, old_ldt->entries, old_nr_entries * LDT_ENTRY_SIZE); new_ldt->entries[ldt_info.entry_number] = ldt; finalize_ldt_struct(new_ldt); /* * If we are using PTI, map the new LDT into the userspace pagetables. * If there is already an LDT, use the other slot so that other CPUs * will continue to use the old LDT until install_ldt() switches * them over to the new LDT. */ error = map_ldt_struct(mm, new_ldt, old_ldt ? !old_ldt->slot : 0); if (error) { /* * This only can fail for the first LDT setup. If an LDT is * already installed then the PTE page is already * populated. Mop up a half populated page table. */ if (!WARN_ON_ONCE(old_ldt)) free_ldt_pgtables(mm); free_ldt_struct(new_ldt); goto out_unlock; } install_ldt(mm, new_ldt); unmap_ldt_struct(mm, old_ldt); free_ldt_struct(old_ldt); error = 0; out_unlock: up_write(&mm->context.ldt_usr_sem); out: return error; } SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , unsigned long , bytecount) { int ret = -ENOSYS; switch (func) { case 0: ret = read_ldt(ptr, bytecount); break; case 1: ret = write_ldt(ptr, bytecount, 1); break; case 2: ret = read_default_ldt(ptr, bytecount); break; case 0x11: ret = write_ldt(ptr, bytecount, 0); break; } /* * The SYSCALL_DEFINE() macros give us an 'unsigned long' * return type, but the ABI for sys_modify_ldt() expects * 'int'. This cast gives us an int-sized value in %rax * for the return code. The 'unsigned' is necessary so * the compiler does not try to sign-extend the negative * return codes into the high half of the register when * taking the value from int->long. */ return (unsigned int)ret; } |
| 246 847 847 848 691 687 205 204 204 203 203 133 114 114 114 133 133 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 IBM Corporation * * Author: * Mimi Zohar <zohar@us.ibm.com> */ #include <linux/module.h> #include <linux/init.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/xattr.h> #include <linux/magic.h> #include <linux/ima.h> #include <linux/evm.h> #include <linux/fsverity.h> #include <keys/system_keyring.h> #include <uapi/linux/fsverity.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM static char *ima_appraise_cmdline_default __initdata; core_param(ima_appraise, ima_appraise_cmdline_default, charp, 0); void __init ima_appraise_parse_cmdline(void) { const char *str = ima_appraise_cmdline_default; bool sb_state = arch_ima_get_secureboot(); int appraisal_state = ima_appraise; if (!str) return; if (strncmp(str, "off", 3) == 0) appraisal_state = 0; else if (strncmp(str, "log", 3) == 0) appraisal_state = IMA_APPRAISE_LOG; else if (strncmp(str, "fix", 3) == 0) appraisal_state = IMA_APPRAISE_FIX; else if (strncmp(str, "enforce", 7) == 0) appraisal_state = IMA_APPRAISE_ENFORCE; else pr_err("invalid \"%s\" appraise option", str); /* If appraisal state was changed, but secure boot is enabled, * keep its default */ if (sb_state) { if (!(appraisal_state & IMA_APPRAISE_ENFORCE)) pr_info("Secure boot enabled: ignoring ima_appraise=%s option", str); } else { ima_appraise = appraisal_state; } } #endif /* * is_ima_appraise_enabled - return appraise status * * Only return enabled, if not in ima_appraise="fix" or "log" modes. */ bool is_ima_appraise_enabled(void) { return ima_appraise & IMA_APPRAISE_ENFORCE; } /* * ima_must_appraise - set appraise flag * * Return 1 to appraise or hash */ int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode, int mask, enum ima_hooks func) { u32 secid; if (!ima_appraise) return 0; security_current_getsecid_subj(&secid); return ima_match_policy(idmap, inode, current_cred(), secid, func, mask, IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL, NULL); } static int ima_fix_xattr(struct dentry *dentry, struct ima_iint_cache *iint) { int rc, offset; u8 algo = iint->ima_hash->algo; if (algo <= HASH_ALGO_SHA1) { offset = 1; iint->ima_hash->xattr.sha1.type = IMA_XATTR_DIGEST; } else { offset = 0; iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG; iint->ima_hash->xattr.ng.algo = algo; } rc = __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, &iint->ima_hash->xattr.data[offset], (sizeof(iint->ima_hash->xattr) - offset) + iint->ima_hash->length, 0); return rc; } /* Return specific func appraised cached result */ enum integrity_status ima_get_cache_status(struct ima_iint_cache *iint, enum ima_hooks func) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: return iint->ima_mmap_status; case BPRM_CHECK: return iint->ima_bprm_status; case CREDS_CHECK: return iint->ima_creds_status; case FILE_CHECK: case POST_SETATTR: return iint->ima_file_status; case MODULE_CHECK ... MAX_CHECK - 1: default: return iint->ima_read_status; } } static void ima_set_cache_status(struct ima_iint_cache *iint, enum ima_hooks func, enum integrity_status status) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: iint->ima_mmap_status = status; break; case BPRM_CHECK: iint->ima_bprm_status = status; break; case CREDS_CHECK: iint->ima_creds_status = status; break; case FILE_CHECK: case POST_SETATTR: iint->ima_file_status = status; break; case MODULE_CHECK ... MAX_CHECK - 1: default: iint->ima_read_status = status; break; } } static void ima_cache_flags(struct ima_iint_cache *iint, enum ima_hooks func) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: iint->flags |= (IMA_MMAP_APPRAISED | IMA_APPRAISED); break; case BPRM_CHECK: iint->flags |= (IMA_BPRM_APPRAISED | IMA_APPRAISED); break; case CREDS_CHECK: iint->flags |= (IMA_CREDS_APPRAISED | IMA_APPRAISED); break; case FILE_CHECK: case POST_SETATTR: iint->flags |= (IMA_FILE_APPRAISED | IMA_APPRAISED); break; case MODULE_CHECK ... MAX_CHECK - 1: default: iint->flags |= (IMA_READ_APPRAISED | IMA_APPRAISED); break; } } enum hash_algo ima_get_hash_algo(const struct evm_ima_xattr_data *xattr_value, int xattr_len) { struct signature_v2_hdr *sig; enum hash_algo ret; if (!xattr_value || xattr_len < 2) /* return default hash algo */ return ima_hash_algo; switch (xattr_value->type) { case IMA_VERITY_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 3 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; case EVM_IMA_XATTR_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 2 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ ret = xattr_value->data[0]; if (ret < HASH_ALGO__LAST) return ret; break; case IMA_XATTR_DIGEST: /* this is for backward compatibility */ if (xattr_len == 21) { unsigned int zero = 0; if (!memcmp(&xattr_value->data[16], &zero, 4)) return HASH_ALGO_MD5; else return HASH_ALGO_SHA1; } else if (xattr_len == 17) return HASH_ALGO_MD5; break; } /* return default hash algo */ return ima_hash_algo; } int ima_read_xattr(struct dentry *dentry, struct evm_ima_xattr_data **xattr_value, int xattr_len) { int ret; ret = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, (char **)xattr_value, xattr_len, GFP_NOFS); if (ret == -EOPNOTSUPP) ret = 0; return ret; } /* * calc_file_id_hash - calculate the hash of the ima_file_id struct data * @type: xattr type [enum evm_ima_xattr_type] * @algo: hash algorithm [enum hash_algo] * @digest: pointer to the digest to be hashed * @hash: (out) pointer to the hash * * IMA signature version 3 disambiguates the data that is signed by * indirectly signing the hash of the ima_file_id structure data. * * Signing the ima_file_id struct is currently only supported for * IMA_VERITY_DIGSIG type xattrs. * * Return 0 on success, error code otherwise. */ static int calc_file_id_hash(enum evm_ima_xattr_type type, enum hash_algo algo, const u8 *digest, struct ima_digest_data *hash) { struct ima_file_id file_id = { .hash_type = IMA_VERITY_DIGSIG, .hash_algorithm = algo}; unsigned int unused = HASH_MAX_DIGESTSIZE - hash_digest_size[algo]; if (type != IMA_VERITY_DIGSIG) return -EINVAL; memcpy(file_id.hash, digest, hash_digest_size[algo]); hash->algo = algo; hash->length = hash_digest_size[algo]; return ima_calc_buffer_hash(&file_id, sizeof(file_id) - unused, hash); } /* * xattr_verify - verify xattr digest or signature * * Verify whether the hash or signature matches the file contents. * * Return 0 on success, error code otherwise. */ static int xattr_verify(enum ima_hooks func, struct ima_iint_cache *iint, struct evm_ima_xattr_data *xattr_value, int xattr_len, enum integrity_status *status, const char **cause) { struct ima_max_digest_data hash; struct signature_v2_hdr *sig; int rc = -EINVAL, hash_start = 0; int mask; switch (xattr_value->type) { case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ hash_start = 1; fallthrough; case IMA_XATTR_DIGEST: if (*status != INTEGRITY_PASS_IMMUTABLE) { if (iint->flags & IMA_DIGSIG_REQUIRED) { if (iint->flags & IMA_VERITY_REQUIRED) *cause = "verity-signature-required"; else *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } clear_bit(IMA_DIGSIG, &iint->atomic_flags); } else { set_bit(IMA_DIGSIG, &iint->atomic_flags); } if (xattr_len - sizeof(xattr_value->type) - hash_start >= iint->ima_hash->length) /* * xattr length may be longer. md5 hash in previous * version occupied 20 bytes in xattr, instead of 16 */ rc = memcmp(&xattr_value->data[hash_start], iint->ima_hash->digest, iint->ima_hash->length); else rc = -EINVAL; if (rc) { *cause = "invalid-hash"; *status = INTEGRITY_FAIL; break; } *status = INTEGRITY_PASS; break; case EVM_IMA_XATTR_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); mask = IMA_DIGSIG_REQUIRED | IMA_VERITY_REQUIRED; if ((iint->flags & mask) == mask) { *cause = "verity-signature-required"; *status = INTEGRITY_FAIL; break; } sig = (typeof(sig))xattr_value; if (sig->version >= 3) { *cause = "invalid-signature-version"; *status = INTEGRITY_FAIL; break; } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc == -EOPNOTSUPP) { *status = INTEGRITY_UNKNOWN; break; } if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && func == KEXEC_KERNEL_CHECK) rc = integrity_digsig_verify(INTEGRITY_KEYRING_PLATFORM, (const char *)xattr_value, xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc) { *cause = "invalid-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } break; case IMA_VERITY_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); if (iint->flags & IMA_DIGSIG_REQUIRED) { if (!(iint->flags & IMA_VERITY_REQUIRED)) { *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } } sig = (typeof(sig))xattr_value; if (sig->version != 3) { *cause = "invalid-signature-version"; *status = INTEGRITY_FAIL; break; } rc = calc_file_id_hash(IMA_VERITY_DIGSIG, iint->ima_hash->algo, iint->ima_hash->digest, container_of(&hash.hdr, struct ima_digest_data, hdr)); if (rc) { *cause = "sigv3-hashing-error"; *status = INTEGRITY_FAIL; break; } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, hash.digest, hash.hdr.length); if (rc) { *cause = "invalid-verity-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } break; default: *status = INTEGRITY_UNKNOWN; *cause = "unknown-ima-data"; break; } return rc; } /* * modsig_verify - verify modsig signature * * Verify whether the signature matches the file contents. * * Return 0 on success, error code otherwise. */ static int modsig_verify(enum ima_hooks func, const struct modsig *modsig, enum integrity_status *status, const char **cause) { int rc; rc = integrity_modsig_verify(INTEGRITY_KEYRING_IMA, modsig); if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && func == KEXEC_KERNEL_CHECK) rc = integrity_modsig_verify(INTEGRITY_KEYRING_PLATFORM, modsig); if (rc) { *cause = "invalid-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } return rc; } /* * ima_check_blacklist - determine if the binary is blacklisted. * * Add the hash of the blacklisted binary to the measurement list, based * on policy. * * Returns -EPERM if the hash is blacklisted. */ int ima_check_blacklist(struct ima_iint_cache *iint, const struct modsig *modsig, int pcr) { enum hash_algo hash_algo; const u8 *digest = NULL; u32 digestsize = 0; int rc = 0; if (!(iint->flags & IMA_CHECK_BLACKLIST)) return 0; if (iint->flags & IMA_MODSIG_ALLOWED && modsig) { ima_get_modsig_digest(modsig, &hash_algo, &digest, &digestsize); rc = is_binary_blacklisted(digest, digestsize); } else if (iint->flags & IMA_DIGSIG_REQUIRED && iint->ima_hash) rc = is_binary_blacklisted(iint->ima_hash->digest, iint->ima_hash->length); if ((rc == -EPERM) && (iint->flags & IMA_MEASURE)) process_buffer_measurement(&nop_mnt_idmap, NULL, digest, digestsize, "blacklisted-hash", NONE, pcr, NULL, false, NULL, 0); return rc; } /* * ima_appraise_measurement - appraise file measurement * * Call evm_verifyxattr() to verify the integrity of 'security.ima'. * Assuming success, compare the xattr hash with the collected measurement. * * Return 0 on success, error code otherwise */ int ima_appraise_measurement(enum ima_hooks func, struct ima_iint_cache *iint, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig) { static const char op[] = "appraise_data"; const char *cause = "unknown"; struct dentry *dentry = file_dentry(file); struct inode *inode = d_backing_inode(dentry); enum integrity_status status = INTEGRITY_UNKNOWN; int rc = xattr_len; bool try_modsig = iint->flags & IMA_MODSIG_ALLOWED && modsig; /* If not appraising a modsig, we need an xattr. */ if (!(inode->i_opflags & IOP_XATTR) && !try_modsig) return INTEGRITY_UNKNOWN; /* If reading the xattr failed and there's no modsig, error out. */ if (rc <= 0 && !try_modsig) { if (rc && rc != -ENODATA) goto out; if (iint->flags & IMA_DIGSIG_REQUIRED) { if (iint->flags & IMA_VERITY_REQUIRED) cause = "verity-signature-required"; else cause = "IMA-signature-required"; } else { cause = "missing-hash"; } status = INTEGRITY_NOLABEL; if (file->f_mode & FMODE_CREATED) iint->flags |= IMA_NEW_FILE; if ((iint->flags & IMA_NEW_FILE) && (!(iint->flags & IMA_DIGSIG_REQUIRED) || (inode->i_size == 0))) status = INTEGRITY_PASS; goto out; } status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value, rc < 0 ? 0 : rc); switch (status) { case INTEGRITY_PASS: case INTEGRITY_PASS_IMMUTABLE: case INTEGRITY_UNKNOWN: break; case INTEGRITY_NOXATTRS: /* No EVM protected xattrs. */ /* It's fine not to have xattrs when using a modsig. */ if (try_modsig) break; fallthrough; case INTEGRITY_NOLABEL: /* No security.evm xattr. */ cause = "missing-HMAC"; goto out; case INTEGRITY_FAIL_IMMUTABLE: set_bit(IMA_DIGSIG, &iint->atomic_flags); cause = "invalid-fail-immutable"; goto out; case INTEGRITY_FAIL: /* Invalid HMAC/signature. */ cause = "invalid-HMAC"; goto out; default: WARN_ONCE(true, "Unexpected integrity status %d\n", status); } if (xattr_value) rc = xattr_verify(func, iint, xattr_value, xattr_len, &status, &cause); /* * If we have a modsig and either no imasig or the imasig's key isn't * known, then try verifying the modsig. */ if (try_modsig && (!xattr_value || xattr_value->type == IMA_XATTR_DIGEST_NG || rc == -ENOKEY)) rc = modsig_verify(func, modsig, &status, &cause); out: /* * File signatures on some filesystems can not be properly verified. * When such filesystems are mounted by an untrusted mounter or on a * system not willing to accept such a risk, fail the file signature * verification. */ if ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && ((inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) || (iint->flags & IMA_FAIL_UNVERIFIABLE_SIGS))) { status = INTEGRITY_FAIL; cause = "unverifiable-signature"; integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, filename, op, cause, rc, 0); } else if (status != INTEGRITY_PASS) { /* Fix mode, but don't replace file signatures. */ if ((ima_appraise & IMA_APPRAISE_FIX) && !try_modsig && (!xattr_value || xattr_value->type != EVM_IMA_XATTR_DIGSIG)) { if (!ima_fix_xattr(dentry, iint)) status = INTEGRITY_PASS; } /* * Permit new files with file/EVM portable signatures, but * without data. */ if (inode->i_size == 0 && iint->flags & IMA_NEW_FILE && test_bit(IMA_DIGSIG, &iint->atomic_flags)) { status = INTEGRITY_PASS; } integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, filename, op, cause, rc, 0); } else { ima_cache_flags(iint, func); } ima_set_cache_status(iint, func, status); return status; } /* * ima_update_xattr - update 'security.ima' hash value */ void ima_update_xattr(struct ima_iint_cache *iint, struct file *file) { struct dentry *dentry = file_dentry(file); int rc = 0; /* do not collect and update hash for digital signatures */ if (test_bit(IMA_DIGSIG, &iint->atomic_flags)) return; if ((iint->ima_file_status != INTEGRITY_PASS) && !(iint->flags & IMA_HASH)) return; rc = ima_collect_measurement(iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) return; inode_lock(file_inode(file)); ima_fix_xattr(dentry, iint); inode_unlock(file_inode(file)); } /** * ima_inode_post_setattr - reflect file metadata changes * @idmap: idmap of the mount the inode was found from * @dentry: pointer to the affected dentry * @ia_valid: for the UID and GID status * * Changes to a dentry's metadata might result in needing to appraise. * * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ static void ima_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { struct inode *inode = d_backing_inode(dentry); struct ima_iint_cache *iint; int action; if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode) || !(inode->i_opflags & IOP_XATTR)) return; action = ima_must_appraise(idmap, inode, MAY_ACCESS, POST_SETATTR); iint = ima_iint_find(inode); if (iint) { set_bit(IMA_CHANGE_ATTR, &iint->atomic_flags); if (!action) clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } } /* * ima_protect_xattr - protect 'security.ima' * * Ensure that not just anyone can modify or remove 'security.ima'. */ static int ima_protect_xattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { if (strcmp(xattr_name, XATTR_NAME_IMA) == 0) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 1; } return 0; } static void ima_reset_appraise_flags(struct inode *inode, int digsig) { struct ima_iint_cache *iint; if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; iint->measured_pcrs = 0; set_bit(IMA_CHANGE_XATTR, &iint->atomic_flags); if (digsig) set_bit(IMA_DIGSIG, &iint->atomic_flags); else clear_bit(IMA_DIGSIG, &iint->atomic_flags); } /** * validate_hash_algo() - Block setxattr with unsupported hash algorithms * @dentry: object of the setxattr() * @xattr_value: userland supplied xattr value * @xattr_value_len: length of xattr_value * * The xattr value is mapped to its hash algorithm, and this algorithm * must be built in the kernel for the setxattr to be allowed. * * Emit an audit message when the algorithm is invalid. * * Return: 0 on success, else an error. */ static int validate_hash_algo(struct dentry *dentry, const struct evm_ima_xattr_data *xattr_value, size_t xattr_value_len) { char *path = NULL, *pathbuf = NULL; enum hash_algo xattr_hash_algo; const char *errmsg = "unavailable-hash-algorithm"; unsigned int allowed_hashes; xattr_hash_algo = ima_get_hash_algo(xattr_value, xattr_value_len); allowed_hashes = atomic_read(&ima_setxattr_allowed_hash_algorithms); if (allowed_hashes) { /* success if the algorithm is allowed in the ima policy */ if (allowed_hashes & (1U << xattr_hash_algo)) return 0; /* * We use a different audit message when the hash algorithm * is denied by a policy rule, instead of not being built * in the kernel image */ errmsg = "denied-hash-algorithm"; } else { if (likely(xattr_hash_algo == ima_hash_algo)) return 0; /* allow any xattr using an algorithm built in the kernel */ if (crypto_has_alg(hash_algo_name[xattr_hash_algo], 0, 0)) return 0; } pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf) return -EACCES; path = dentry_path(dentry, pathbuf, PATH_MAX); integrity_audit_msg(AUDIT_INTEGRITY_DATA, d_inode(dentry), path, "set_data", errmsg, -EACCES, 0); kfree(pathbuf); return -EACCES; } static int ima_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { const struct evm_ima_xattr_data *xvalue = xattr_value; int digsig = 0; int result; int err; result = ima_protect_xattr(dentry, xattr_name, xattr_value, xattr_value_len); if (result == 1) { if (!xattr_value_len || (xvalue->type >= IMA_XATTR_LAST)) return -EINVAL; err = validate_hash_algo(dentry, xvalue, xattr_value_len); if (err) return err; digsig = (xvalue->type == EVM_IMA_XATTR_DIGSIG); } else if (!strcmp(xattr_name, XATTR_NAME_EVM) && xattr_value_len > 0) { digsig = (xvalue->type == EVM_XATTR_PORTABLE_DIGSIG); } if (result == 1 || evm_revalidate_status(xattr_name)) { ima_reset_appraise_flags(d_backing_inode(dentry), digsig); if (result == 1) result = 0; } return result; } static int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (evm_revalidate_status(acl_name)) ima_reset_appraise_flags(d_backing_inode(dentry), 0); return 0; } static int ima_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { int result; result = ima_protect_xattr(dentry, xattr_name, NULL, 0); if (result == 1 || evm_revalidate_status(xattr_name)) { ima_reset_appraise_flags(d_backing_inode(dentry), 0); if (result == 1) result = 0; } return result; } static int ima_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return ima_inode_set_acl(idmap, dentry, acl_name, NULL); } static struct security_hook_list ima_appraise_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_post_setattr, ima_inode_post_setattr), LSM_HOOK_INIT(inode_setxattr, ima_inode_setxattr), LSM_HOOK_INIT(inode_set_acl, ima_inode_set_acl), LSM_HOOK_INIT(inode_removexattr, ima_inode_removexattr), LSM_HOOK_INIT(inode_remove_acl, ima_inode_remove_acl), }; void __init init_ima_appraise_lsm(const struct lsm_id *lsmid) { security_add_hooks(ima_appraise_hooks, ARRAY_SIZE(ima_appraise_hooks), lsmid); } |
| 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2020 Facebook * Copyright 2020 Google LLC. */ #include <linux/pid.h> #include <linux/sched.h> #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/bpf_local_storage.h> #include <linux/filter.h> #include <uapi/linux/btf.h> #include <linux/btf_ids.h> #include <linux/fdtable.h> #include <linux/rcupdate_trace.h> DEFINE_BPF_STORAGE_CACHE(task_cache); static DEFINE_PER_CPU(int, bpf_task_storage_busy); static void bpf_task_storage_lock(void) { migrate_disable(); this_cpu_inc(bpf_task_storage_busy); } static void bpf_task_storage_unlock(void) { this_cpu_dec(bpf_task_storage_busy); migrate_enable(); } static bool bpf_task_storage_trylock(void) { migrate_disable(); if (unlikely(this_cpu_inc_return(bpf_task_storage_busy) != 1)) { this_cpu_dec(bpf_task_storage_busy); migrate_enable(); return false; } return true; } static struct bpf_local_storage __rcu **task_storage_ptr(void *owner) { struct task_struct *task = owner; return &task->bpf_storage; } static struct bpf_local_storage_data * task_storage_lookup(struct task_struct *task, struct bpf_map *map, bool cacheit_lockit) { struct bpf_local_storage *task_storage; struct bpf_local_storage_map *smap; task_storage = rcu_dereference_check(task->bpf_storage, bpf_rcu_lock_held()); if (!task_storage) return NULL; smap = (struct bpf_local_storage_map *)map; return bpf_local_storage_lookup(task_storage, smap, cacheit_lockit); } void bpf_task_storage_free(struct task_struct *task) { struct bpf_local_storage *local_storage; rcu_read_lock(); local_storage = rcu_dereference(task->bpf_storage); if (!local_storage) { rcu_read_unlock(); return; } bpf_task_storage_lock(); bpf_local_storage_destroy(local_storage); bpf_task_storage_unlock(); rcu_read_unlock(); } static void *bpf_pid_task_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; struct task_struct *task; unsigned int f_flags; struct pid *pid; int fd, err; fd = *(int *)key; pid = pidfd_get_pid(fd, &f_flags); if (IS_ERR(pid)) return ERR_CAST(pid); /* We should be in an RCU read side critical section, it should be safe * to call pid_task. */ WARN_ON_ONCE(!rcu_read_lock_held()); task = pid_task(pid, PIDTYPE_PID); if (!task) { err = -ENOENT; goto out; } bpf_task_storage_lock(); sdata = task_storage_lookup(task, map, true); bpf_task_storage_unlock(); put_pid(pid); return sdata ? sdata->data : NULL; out: put_pid(pid); return ERR_PTR(err); } static long bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct task_struct *task; unsigned int f_flags; struct pid *pid; int fd, err; fd = *(int *)key; pid = pidfd_get_pid(fd, &f_flags); if (IS_ERR(pid)) return PTR_ERR(pid); /* We should be in an RCU read side critical section, it should be safe * to call pid_task. */ WARN_ON_ONCE(!rcu_read_lock_held()); task = pid_task(pid, PIDTYPE_PID); if (!task) { err = -ENOENT; goto out; } bpf_task_storage_lock(); sdata = bpf_local_storage_update( task, (struct bpf_local_storage_map *)map, value, map_flags, GFP_ATOMIC); bpf_task_storage_unlock(); err = PTR_ERR_OR_ZERO(sdata); out: put_pid(pid); return err; } static int task_storage_delete(struct task_struct *task, struct bpf_map *map, bool nobusy) { struct bpf_local_storage_data *sdata; sdata = task_storage_lookup(task, map, false); if (!sdata) return -ENOENT; if (!nobusy) return -EBUSY; bpf_selem_unlink(SELEM(sdata), false); return 0; } static long bpf_pid_task_storage_delete_elem(struct bpf_map *map, void *key) { struct task_struct *task; unsigned int f_flags; struct pid *pid; int fd, err; fd = *(int *)key; pid = pidfd_get_pid(fd, &f_flags); if (IS_ERR(pid)) return PTR_ERR(pid); /* We should be in an RCU read side critical section, it should be safe * to call pid_task. */ WARN_ON_ONCE(!rcu_read_lock_held()); task = pid_task(pid, PIDTYPE_PID); if (!task) { err = -ENOENT; goto out; } bpf_task_storage_lock(); err = task_storage_delete(task, map, true); bpf_task_storage_unlock(); out: put_pid(pid); return err; } /* Called by bpf_task_storage_get*() helpers */ static void *__bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags, gfp_t gfp_flags, bool nobusy) { struct bpf_local_storage_data *sdata; sdata = task_storage_lookup(task, map, nobusy); if (sdata) return sdata->data; /* only allocate new storage, when the task is refcounted */ if (refcount_read(&task->usage) && (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) && nobusy) { sdata = bpf_local_storage_update( task, (struct bpf_local_storage_map *)map, value, BPF_NOEXIST, gfp_flags); return IS_ERR(sdata) ? NULL : sdata->data; } return NULL; } /* *gfp_flags* is a hidden argument provided by the verifier */ BPF_CALL_5(bpf_task_storage_get_recur, struct bpf_map *, map, struct task_struct *, task, void *, value, u64, flags, gfp_t, gfp_flags) { bool nobusy; void *data; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (flags & ~BPF_LOCAL_STORAGE_GET_F_CREATE || !task) return (unsigned long)NULL; nobusy = bpf_task_storage_trylock(); data = __bpf_task_storage_get(map, task, value, flags, gfp_flags, nobusy); if (nobusy) bpf_task_storage_unlock(); return (unsigned long)data; } /* *gfp_flags* is a hidden argument provided by the verifier */ BPF_CALL_5(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, task, void *, value, u64, flags, gfp_t, gfp_flags) { void *data; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (flags & ~BPF_LOCAL_STORAGE_GET_F_CREATE || !task) return (unsigned long)NULL; bpf_task_storage_lock(); data = __bpf_task_storage_get(map, task, value, flags, gfp_flags, true); bpf_task_storage_unlock(); return (unsigned long)data; } BPF_CALL_2(bpf_task_storage_delete_recur, struct bpf_map *, map, struct task_struct *, task) { bool nobusy; int ret; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!task) return -EINVAL; nobusy = bpf_task_storage_trylock(); /* This helper must only be called from places where the lifetime of the task * is guaranteed. Either by being refcounted or by being protected * by an RCU read-side critical section. */ ret = task_storage_delete(task, map, nobusy); if (nobusy) bpf_task_storage_unlock(); return ret; } BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *, task) { int ret; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!task) return -EINVAL; bpf_task_storage_lock(); /* This helper must only be called from places where the lifetime of the task * is guaranteed. Either by being refcounted or by being protected * by an RCU read-side critical section. */ ret = task_storage_delete(task, map, true); bpf_task_storage_unlock(); return ret; } static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr) { return bpf_local_storage_map_alloc(attr, &task_cache, true); } static void task_storage_map_free(struct bpf_map *map) { bpf_local_storage_map_free(map, &task_cache, &bpf_task_storage_busy); } BTF_ID_LIST_GLOBAL_SINGLE(bpf_local_storage_map_btf_id, struct, bpf_local_storage_map) const struct bpf_map_ops task_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, .map_alloc = task_storage_map_alloc, .map_free = task_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_pid_task_storage_lookup_elem, .map_update_elem = bpf_pid_task_storage_update_elem, .map_delete_elem = bpf_pid_task_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, .map_mem_usage = bpf_local_storage_map_mem_usage, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = task_storage_ptr, }; const struct bpf_func_proto bpf_task_storage_get_recur_proto = { .func = bpf_task_storage_get_recur, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_task_storage_get_proto = { .func = bpf_task_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_task_storage_delete_recur_proto = { .func = bpf_task_storage_delete_recur, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; const struct bpf_func_proto bpf_task_storage_delete_proto = { .func = bpf_task_storage_delete, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; |
| 8 8 8 2 1 1 2 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/tty.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/semaphore.h> #include <linux/sched.h> #include "tty.h" /* Legacy tty mutex glue */ /* * Getting the big tty mutex. */ void tty_lock(struct tty_struct *tty) { tty_kref_get(tty); mutex_lock(&tty->legacy_mutex); } EXPORT_SYMBOL(tty_lock); int tty_lock_interruptible(struct tty_struct *tty) { int ret; tty_kref_get(tty); ret = mutex_lock_interruptible(&tty->legacy_mutex); if (ret) tty_kref_put(tty); return ret; } void tty_unlock(struct tty_struct *tty) { mutex_unlock(&tty->legacy_mutex); tty_kref_put(tty); } EXPORT_SYMBOL(tty_unlock); void tty_lock_slave(struct tty_struct *tty) { if (tty && tty != tty->link) tty_lock(tty); } void tty_unlock_slave(struct tty_struct *tty) { if (tty && tty != tty->link) tty_unlock(tty); } void tty_set_lock_subclass(struct tty_struct *tty) { lockdep_set_subclass(&tty->legacy_mutex, TTY_LOCK_SLAVE); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 | /* SPDX-License-Identifier: GPL-2.0 */ /* * workqueue.h --- work queue handling for Linux. */ #ifndef _LINUX_WORKQUEUE_H #define _LINUX_WORKQUEUE_H #include <linux/timer.h> #include <linux/linkage.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cpumask_types.h> #include <linux/rcupdate.h> #include <linux/workqueue_types.h> /* * The first word is the work queue pointer and the flags rolled into * one */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) enum work_bits { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ WORK_STRUCT_INACTIVE_BIT, /* work item is inactive */ WORK_STRUCT_PWQ_BIT, /* data points to pwq */ WORK_STRUCT_LINKED_BIT, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT, /* static initializer (debugobjects) */ #endif WORK_STRUCT_FLAG_BITS, /* color for workqueue flushing */ WORK_STRUCT_COLOR_SHIFT = WORK_STRUCT_FLAG_BITS, WORK_STRUCT_COLOR_BITS = 4, /* * When WORK_STRUCT_PWQ is set, reserve 8 bits off of pwq pointer w/ * debugobjects turned off. This makes pwqs aligned to 256 bytes (512 * bytes w/ DEBUG_OBJECTS_WORK) and allows 16 workqueue flush colors. * * MSB * [ pwq pointer ] [ flush color ] [ STRUCT flags ] * 4 bits 4 or 5 bits */ WORK_STRUCT_PWQ_SHIFT = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, /* * data contains off-queue information when !WORK_STRUCT_PWQ. * * MSB * [ pool ID ] [ disable depth ] [ OFFQ flags ] [ STRUCT flags ] * 16 bits 1 bit 4 or 5 bits */ WORK_OFFQ_FLAG_SHIFT = WORK_STRUCT_FLAG_BITS, WORK_OFFQ_BH_BIT = WORK_OFFQ_FLAG_SHIFT, WORK_OFFQ_FLAG_END, WORK_OFFQ_FLAG_BITS = WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT, WORK_OFFQ_DISABLE_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_DISABLE_BITS = 16, /* * When a work item is off queue, the high bits encode off-queue flags * and the last pool it was on. Cap pool ID to 31 bits and use the * highest number to indicate that no pool is associated. */ WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_DISABLE_SHIFT + WORK_OFFQ_DISABLE_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, }; enum work_flags { WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, #else WORK_STRUCT_STATIC = 0, #endif }; enum wq_misc_consts { WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS), /* not bound to any CPU, prefer the local CPU */ WORK_CPU_UNBOUND = NR_CPUS, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ WORKER_DESC_LEN = 32, }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ #define WORK_OFFQ_BH (1ul << WORK_OFFQ_BH_BIT) #define WORK_OFFQ_FLAG_MASK (((1ul << WORK_OFFQ_FLAG_BITS) - 1) << WORK_OFFQ_FLAG_SHIFT) #define WORK_OFFQ_DISABLE_MASK (((1ul << WORK_OFFQ_DISABLE_BITS) - 1) << WORK_OFFQ_DISABLE_SHIFT) #define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) #define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) #define WORK_STRUCT_PWQ_MASK (~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1)) #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) struct delayed_work { struct work_struct work; struct timer_list timer; /* target workqueue and CPU ->timer uses to queue ->work */ struct workqueue_struct *wq; int cpu; }; struct rcu_work { struct work_struct work; struct rcu_head rcu; /* target workqueue ->rcu uses to queue ->work */ struct workqueue_struct *wq; }; enum wq_affn_scope { WQ_AFFN_DFL, /* use system default */ WQ_AFFN_CPU, /* one pod per CPU */ WQ_AFFN_SMT, /* one pod poer SMT */ WQ_AFFN_CACHE, /* one pod per LLC */ WQ_AFFN_NUMA, /* one pod per NUMA node */ WQ_AFFN_SYSTEM, /* one pod across the whole system */ WQ_AFFN_NR_TYPES, }; /** * struct workqueue_attrs - A struct for workqueue attributes. * * This can be used to change attributes of an unbound workqueue. */ struct workqueue_attrs { /** * @nice: nice level */ int nice; /** * @cpumask: allowed CPUs * * Work items in this workqueue are affine to these CPUs and not allowed * to execute on other CPUs. A pool serving a workqueue must have the * same @cpumask. */ cpumask_var_t cpumask; /** * @__pod_cpumask: internal attribute used to create per-pod pools * * Internal use only. * * Per-pod unbound worker pools are used to improve locality. Always a * subset of ->cpumask. A workqueue can be associated with multiple * worker pools with disjoint @__pod_cpumask's. Whether the enforcement * of a pool's @__pod_cpumask is strict depends on @affn_strict. */ cpumask_var_t __pod_cpumask; /** * @affn_strict: affinity scope is strict * * If clear, workqueue will make a best-effort attempt at starting the * worker inside @__pod_cpumask but the scheduler is free to migrate it * outside. * * If set, workers are only allowed to run inside @__pod_cpumask. */ bool affn_strict; /* * Below fields aren't properties of a worker_pool. They only modify how * :c:func:`apply_workqueue_attrs` select pools and thus don't * participate in pool hash calculations or equality comparisons. * * If @affn_strict is set, @cpumask isn't a property of a worker_pool * either. */ /** * @affn_scope: unbound CPU affinity scope * * CPU pods are used to improve execution locality of unbound work * items. There are multiple pod types, one for each wq_affn_scope, and * every CPU in the system belongs to one pod in every pod type. CPUs * that belong to the same pod share the worker pool. For example, * selecting %WQ_AFFN_NUMA makes the workqueue use a separate worker * pool for each NUMA node. */ enum wq_affn_scope affn_scope; /** * @ordered: work items must be executed one by one in queueing order */ bool ordered; }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); } static inline struct rcu_work *to_rcu_work(struct work_struct *work) { return container_of(work, struct rcu_work, work); } struct execute_work { struct work_struct work; }; #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting _key * here is required, otherwise it could get initialised to the * copy of the lockdep_map! */ #define __WORK_INIT_LOCKDEP_MAP(n, k) \ .lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k), #else #define __WORK_INIT_LOCKDEP_MAP(n, k) #endif #define __WORK_INITIALIZER(n, f) { \ .data = WORK_DATA_STATIC_INIT(), \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ __WORK_INIT_LOCKDEP_MAP(#n, &(n)) \ } #define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ .timer = __TIMER_INITIALIZER(delayed_work_timer_fn,\ (tflags) | TIMER_IRQSAFE), \ } #define DECLARE_WORK(n, f) \ struct work_struct n = __WORK_INITIALIZER(n, f) #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) #define DECLARE_DEFERRABLE_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE) #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); extern void destroy_delayed_work_on_stack(struct delayed_work *work); static inline unsigned int work_static(struct work_struct *work) { return *work_data_bits(work) & WORK_STRUCT_STATIC; } #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } static inline void destroy_delayed_work_on_stack(struct delayed_work *work) { } static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif /* * initialize all of a work item in one go * * NOTE! No point in using "atomic_long_set()": using a direct * assignment of the work data initializer allows the compiler * to generate better code. */ #ifdef CONFIG_LOCKDEP #define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, (_key), 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #else #define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #endif #define __INIT_WORK(_work, _func, _onstack) \ do { \ static __maybe_unused struct lock_class_key __key; \ \ __INIT_WORK_KEY(_work, _func, _onstack, &__key); \ } while (0) #define INIT_WORK(_work, _func) \ __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ __INIT_WORK((_work), (_func), 1) #define INIT_WORK_ONSTACK_KEY(_work, _func, _key) \ __INIT_WORK_KEY((_work), (_func), 1, _key) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ __init_timer(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define __INIT_DELAYED_WORK_ONSTACK(_work, _func, _tflags) \ do { \ INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ __init_timer_on_stack(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define INIT_DELAYED_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, 0) #define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, 0) #define INIT_DEFERRABLE_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, TIMER_DEFERRABLE) #define INIT_DEFERRABLE_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, TIMER_DEFERRABLE) #define INIT_RCU_WORK(_work, _func) \ INIT_WORK(&(_work)->work, (_func)) #define INIT_RCU_WORK_ONSTACK(_work, _func) \ INIT_WORK_ONSTACK(&(_work)->work, (_func)) /** * work_pending - Find out whether a work item is currently pending * @work: The work item in question */ #define work_pending(work) \ test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) /** * delayed_work_pending - Find out whether a delayable work item is currently * pending * @w: The work item in question */ #define delayed_work_pending(w) \ work_pending(&(w)->work) /* * Workqueue flags and constants. For details, please refer to * Documentation/core-api/workqueue.rst. */ enum wq_flags { WQ_BH = 1 << 0, /* execute in bottom half (softirq) context */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */ WQ_SYSFS = 1 << 6, /* visible in sysfs, see workqueue_sysfs_register() */ /* * Per-cpu workqueues are generally preferred because they tend to * show better performance thanks to cache locality. Per-cpu * workqueues exclude the scheduler from choosing the CPU to * execute the worker threads, which has an unfortunate side effect * of increasing power consumption. * * The scheduler considers a CPU idle if it doesn't have any task * to execute and tries to keep idle cores idle to conserve power; * however, for example, a per-cpu work item scheduled from an * interrupt handler on an idle CPU will force the scheduler to * execute the work item on that CPU breaking the idleness, which in * turn may lead to more scheduling choices which are sub-optimal * in terms of power consumption. * * Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default * but become unbound if workqueue.power_efficient kernel param is * specified. Per-cpu workqueues which are identified to * contribute significantly to power-consumption are identified and * marked with this flag and enabling the power_efficient mode * leads to noticeable power saving at the cost of small * performance disadvantage. * * http://thread.gmane.org/gmane.linux.kernel/1480396 */ WQ_POWER_EFFICIENT = 1 << 7, __WQ_DESTROYING = 1 << 15, /* internal: workqueue is destroying */ __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ /* BH wq only allows the following flags */ __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI, }; enum wq_consts { WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_UNBOUND_MAX_ACTIVE = WQ_MAX_ACTIVE, WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, /* * Per-node default cap on min_active. Unless explicitly set, min_active * is set to min(max_active, WQ_DFL_MIN_ACTIVE). For more details, see * workqueue_struct->min_active definition. */ WQ_DFL_MIN_ACTIVE = 8, }; /* * System-wide workqueues which are always present. * * system_wq is the one used by schedule[_delayed]_work[_on](). * Multi-CPU multi-threaded. There are users which expect relatively * short queue flush time. Don't queue works which can run for too * long. * * system_highpri_wq is similar to system_wq but for work items which * require WQ_HIGHPRI. * * system_long_wq is similar to system_wq but may host long running * works. Queue flushing might take relatively long. * * system_unbound_wq is unbound workqueue. Workers are not bound to * any specific CPU, not concurrency managed, and all queued works are * executed immediately as long as max_active limit is not reached and * resources are available. * * system_freezable_wq is equivalent to system_wq except that it's * freezable. * * *_power_efficient_wq are inclined towards saving power and converted * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise, * they are same as their non-power-efficient counterparts - e.g. * system_power_efficient_wq is identical to system_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. * * system_bh[_highpri]_wq are convenience interface to softirq. BH work items * are executed in the queueing CPU's BH context in the queueing order. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_highpri_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; extern struct workqueue_struct *system_bh_wq; extern struct workqueue_struct *system_bh_highpri_wq; void workqueue_softirq_action(bool highpri); void workqueue_softirq_dead(unsigned int cpu); /** * alloc_workqueue - allocate a workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * @...: args for @fmt * * For a per-cpu workqueue, @max_active limits the number of in-flight work * items for each CPU. e.g. @max_active of 1 indicates that each CPU can be * executing at most one work item for the workqueue. * * For unbound workqueues, @max_active limits the number of in-flight work items * for the whole system. e.g. @max_active of 16 indicates that that there can be * at most 16 work items executing for the workqueue in the whole system. * * As sharing the same active counter for an unbound workqueue across multiple * NUMA nodes can be expensive, @max_active is distributed to each NUMA node * according to the proportion of the number of online CPUs and enforced * independently. * * Depending on online CPU distribution, a node may end up with per-node * max_active which is significantly lower than @max_active, which can lead to * deadlocks if the per-node concurrency limit is lower than the maximum number * of interdependent work items for the workqueue. * * To guarantee forward progress regardless of online CPU distribution, the * concurrency limit on every node is guaranteed to be equal to or greater than * min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means * that the sum of per-node max_active's may be larger than @max_active. * * For detailed information on %WQ_* flags, please refer to * Documentation/core-api/workqueue.rst. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(1, 4) struct workqueue_struct * alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); /** * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @args: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are * implemented as unbound workqueues with @max_active of one. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name)) #define create_freezable_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \ WQ_MEM_RECLAIM, 1, (name)) #define create_singlethread_workqueue(name) \ alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name) #define from_work(var, callback_work, work_fieldname) \ container_of(callback_work, typeof(*var), work_fieldname) extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs(void); void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); extern int workqueue_unbound_exclude_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); extern void __flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern bool disable_work(struct work_struct *work); extern bool disable_work_sync(struct work_struct *work); extern bool enable_work(struct work_struct *work); extern bool disable_delayed_work(struct delayed_work *dwork); extern bool disable_delayed_work_sync(struct delayed_work *dwork); extern bool enable_delayed_work(struct delayed_work *dwork); extern bool flush_rcu_work(struct rcu_work *rwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); extern void workqueue_set_min_active(struct workqueue_struct *wq, int min_active); extern struct work_struct *current_work(void); extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_all_workqueues(void); extern void show_freezable_workqueues(void); extern void show_one_workqueue(struct workqueue_struct *wq); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); /** * queue_work - queue work on a workqueue * @wq: workqueue to use * @work: work to queue * * Returns %false if @work was already on a queue, %true otherwise. * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. * * Memory-ordering properties: If it returns %true, guarantees that all stores * preceding the call to queue_work() in the program order will be visible from * the CPU which will execute @work by the time such work executes, e.g., * * { x is initially 0 } * * CPU0 CPU1 * * WRITE_ONCE(x, 1); [ @work is being executed ] * r0 = queue_work(wq, work); r1 = READ_ONCE(x); * * Forbids: r0 == true && r1 == 0 */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) { return queue_work_on(WORK_CPU_UNBOUND, wq, work); } /** * queue_delayed_work - queue work on a workqueue after delay * @wq: workqueue to use * @dwork: delayable work to queue * @delay: number of jiffies to wait before queueing * * Equivalent to queue_delayed_work_on() but tries to use the local CPU. */ static inline bool queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * mod_delayed_work - modify delay of or queue a delayed work * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * mod_delayed_work_on() on local CPU. */ static inline bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * schedule_work_on - put work task on a specific cpu * @cpu: cpu to put the work task on * @work: job to be done * * This puts a job on a specific cpu */ static inline bool schedule_work_on(int cpu, struct work_struct *work) { return queue_work_on(cpu, system_wq, work); } /** * schedule_work - put work task in global workqueue * @work: job to be done * * Returns %false if @work was already on the kernel-global workqueue and * %true otherwise. * * This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. * * Shares the same memory-ordering properties of queue_work(), cf. the * DocBook header of queue_work(). */ static inline bool schedule_work(struct work_struct *work) { return queue_work(system_wq, work); } /** * enable_and_queue_work - Enable and queue a work item on a specific workqueue * @wq: The target workqueue * @work: The work item to be enabled and queued * * This function combines the operations of enable_work() and queue_work(), * providing a convenient way to enable and queue a work item in a single call. * It invokes enable_work() on @work and then queues it if the disable depth * reached 0. Returns %true if the disable depth reached 0 and @work is queued, * and %false otherwise. * * Note that @work is always queued when disable depth reaches zero. If the * desired behavior is queueing only if certain events took place while @work is * disabled, the user should implement the necessary state tracking and perform * explicit conditional queueing after enable_work(). */ static inline bool enable_and_queue_work(struct workqueue_struct *wq, struct work_struct *work) { if (enable_work(work)) { queue_work(wq, work); return true; } return false; } /* * Detect attempt to flush system-wide workqueues at compile time when possible. * Warn attempt to flush system-wide workqueues at runtime. * * See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp * for reasons and steps for converting system-wide workqueues into local workqueues. */ extern void __warn_flushing_systemwide_wq(void) __compiletime_warning("Please avoid flushing system-wide workqueues."); /* Please stop using this function, for this function will be removed in near future. */ #define flush_scheduled_work() \ ({ \ __warn_flushing_systemwide_wq(); \ __flush_workqueue(system_wq); \ }) #define flush_workqueue(wq) \ ({ \ struct workqueue_struct *_wq = (wq); \ \ if ((__builtin_constant_p(_wq == system_wq) && \ _wq == system_wq) || \ (__builtin_constant_p(_wq == system_highpri_wq) && \ _wq == system_highpri_wq) || \ (__builtin_constant_p(_wq == system_long_wq) && \ _wq == system_long_wq) || \ (__builtin_constant_p(_wq == system_unbound_wq) && \ _wq == system_unbound_wq) || \ (__builtin_constant_p(_wq == system_freezable_wq) && \ _wq == system_freezable_wq) || \ (__builtin_constant_p(_wq == system_power_efficient_wq) && \ _wq == system_power_efficient_wq) || \ (__builtin_constant_p(_wq == system_freezable_power_efficient_wq) && \ _wq == system_freezable_power_efficient_wq)) \ __warn_flushing_systemwide_wq(); \ __flush_workqueue(_wq); \ }) /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use * @dwork: job to be done * @delay: number of jiffies to wait * * After waiting for a given time this puts a job in the kernel-global * workqueue on the specified CPU. */ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(cpu, system_wq, dwork, delay); } /** * schedule_delayed_work - put work task in global workqueue after delay * @dwork: job to be done * @delay: number of jiffies to wait or 0 for immediate execution * * After waiting for a given time this puts a job in the kernel-global * workqueue. */ static inline bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work(system_wq, dwork, delay); } #ifndef CONFIG_SMP static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } #else long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key); /* * A new key is defined for each caller to make sure the work * associated with the function doesn't share its locking class. */ #define work_on_cpu(_cpu, _fn, _arg) \ ({ \ static struct lock_class_key __key; \ \ work_on_cpu_key(_cpu, _fn, _arg, &__key); \ }) long work_on_cpu_safe_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key); /* * A new key is defined for each caller to make sure the work * associated with the function doesn't share its locking class. */ #define work_on_cpu_safe(_cpu, _fn, _arg) \ ({ \ static struct lock_class_key __key; \ \ work_on_cpu_safe_key(_cpu, _fn, _arg, &__key); \ }) #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER extern void freeze_workqueues_begin(void); extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ #ifdef CONFIG_SYSFS int workqueue_sysfs_register(struct workqueue_struct *wq); #else /* CONFIG_SYSFS */ static inline int workqueue_sysfs_register(struct workqueue_struct *wq) { return 0; } #endif /* CONFIG_SYSFS */ #ifdef CONFIG_WQ_WATCHDOG void wq_watchdog_touch(int cpu); #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_touch(int cpu) { } #endif /* CONFIG_WQ_WATCHDOG */ #ifdef CONFIG_SMP int workqueue_prepare_cpu(unsigned int cpu); int workqueue_online_cpu(unsigned int cpu); int workqueue_offline_cpu(unsigned int cpu); #endif void __init workqueue_init_early(void); void __init workqueue_init(void); void __init workqueue_init_topology(void); #endif |
| 5 5 2 3 2 3 2 3 5 5 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 */ /* * jfs_umount.c * * note: file system in transition to aggregate/fileset: * (ref. jfs_mount.c) * * file system unmount is interpreted as mount of the single/only * fileset in the aggregate and, if unmount of the last fileset, * as unmount of the aggerate; */ #include <linux/fs.h> #include "jfs_incore.h" #include "jfs_filsys.h" #include "jfs_superblock.h" #include "jfs_dmap.h" #include "jfs_imap.h" #include "jfs_metapage.h" #include "jfs_debug.h" /* * NAME: jfs_umount(vfsp, flags, crp) * * FUNCTION: vfs_umount() * * PARAMETERS: vfsp - virtual file system pointer * flags - unmount for shutdown * crp - credential * * RETURN : EBUSY - device has open files */ int jfs_umount(struct super_block *sb) { struct jfs_sb_info *sbi = JFS_SBI(sb); struct inode *ipbmap = sbi->ipbmap; struct inode *ipimap = sbi->ipimap; struct inode *ipaimap = sbi->ipaimap; struct inode *ipaimap2 = sbi->ipaimap2; struct jfs_log *log; int rc = 0; jfs_info("UnMount JFS: sb:0x%p", sb); /* * update superblock and close log * * if mounted read-write and log based recovery was enabled */ if ((log = sbi->log)) /* * Wait for outstanding transactions to be written to log: */ jfs_flush_journal(log, 2); /* * close fileset inode allocation map (aka fileset inode) */ diUnmount(ipimap, 0); diFreeSpecial(ipimap); sbi->ipimap = NULL; /* * close secondary aggregate inode allocation map */ if (ipaimap2) { diUnmount(ipaimap2, 0); diFreeSpecial(ipaimap2); sbi->ipaimap2 = NULL; } /* * close aggregate inode allocation map */ diUnmount(ipaimap, 0); diFreeSpecial(ipaimap); sbi->ipaimap = NULL; /* * close aggregate block allocation map */ dbUnmount(ipbmap, 0); diFreeSpecial(ipbmap); sbi->ipbmap = NULL; /* * Make sure all metadata makes it to disk before we mark * the superblock as clean */ filemap_write_and_wait(sbi->direct_inode->i_mapping); /* * ensure all file system file pages are propagated to their * home blocks on disk (and their in-memory buffer pages are * invalidated) BEFORE updating file system superblock state * (to signify file system is unmounted cleanly, and thus in * consistent state) and log superblock active file system * list (to signify skip logredo()). */ if (log) { /* log = NULL if read-only mount */ updateSuper(sb, FM_CLEAN); /* * close log: * * remove file system from log active file system list. */ rc = lmLogClose(sb); } jfs_info("UnMount JFS Complete: rc = %d", rc); return rc; } int jfs_umount_rw(struct super_block *sb) { struct jfs_sb_info *sbi = JFS_SBI(sb); struct jfs_log *log = sbi->log; if (!log) return 0; /* * close log: * * remove file system from log active file system list. */ jfs_flush_journal(log, 2); /* * Make sure all metadata makes it to disk */ dbSync(sbi->ipbmap); diSync(sbi->ipimap); /* * Note that we have to do this even if sync_blockdev() will * do exactly the same a few instructions later: We can't * mark the superblock clean before everything is flushed to * disk. */ filemap_write_and_wait(sbi->direct_inode->i_mapping); updateSuper(sb, FM_CLEAN); return lmLogClose(sb); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions of this file * Copyright(c) 2016-2017 Intel Deutschland GmbH * Copyright (C) 2018, 2021-2024 Intel Corporation */ #ifndef __CFG80211_RDEV_OPS #define __CFG80211_RDEV_OPS #include <linux/rtnetlink.h> #include <net/cfg80211.h> #include "core.h" #include "trace.h" static inline int rdev_suspend(struct cfg80211_registered_device *rdev, struct cfg80211_wowlan *wowlan) { int ret; trace_rdev_suspend(&rdev->wiphy, wowlan); ret = rdev->ops->suspend(&rdev->wiphy, wowlan); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_resume(struct cfg80211_registered_device *rdev) { int ret; trace_rdev_resume(&rdev->wiphy); ret = rdev->ops->resume(&rdev->wiphy); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_set_wakeup(struct cfg80211_registered_device *rdev, bool enabled) { trace_rdev_set_wakeup(&rdev->wiphy, enabled); rdev->ops->set_wakeup(&rdev->wiphy, enabled); trace_rdev_return_void(&rdev->wiphy); } static inline struct wireless_dev *rdev_add_virtual_intf(struct cfg80211_registered_device *rdev, char *name, unsigned char name_assign_type, enum nl80211_iftype type, struct vif_params *params) { struct wireless_dev *ret; trace_rdev_add_virtual_intf(&rdev->wiphy, name, type); ret = rdev->ops->add_virtual_intf(&rdev->wiphy, name, name_assign_type, type, params); trace_rdev_return_wdev(&rdev->wiphy, ret); return ret; } static inline int rdev_del_virtual_intf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { int ret; trace_rdev_del_virtual_intf(&rdev->wiphy, wdev); ret = rdev->ops->del_virtual_intf(&rdev->wiphy, wdev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_virtual_intf(struct cfg80211_registered_device *rdev, struct net_device *dev, enum nl80211_iftype type, struct vif_params *params) { int ret; trace_rdev_change_virtual_intf(&rdev->wiphy, dev, type); ret = rdev->ops->change_virtual_intf(&rdev->wiphy, dev, type, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_add_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr, struct key_params *params) { int ret; trace_rdev_add_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr, params->mode); ret = rdev->ops->add_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr, void *cookie, void (*callback)(void *cookie, struct key_params*)) { int ret; trace_rdev_get_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr); ret = rdev->ops->get_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr, cookie, callback); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr) { int ret; trace_rdev_del_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr); ret = rdev->ops->del_key(&rdev->wiphy, netdev, link_id, key_index, pairwise, mac_addr); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_default_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index, bool unicast, bool multicast) { int ret; trace_rdev_set_default_key(&rdev->wiphy, netdev, link_id, key_index, unicast, multicast); ret = rdev->ops->set_default_key(&rdev->wiphy, netdev, link_id, key_index, unicast, multicast); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_default_mgmt_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index) { int ret; trace_rdev_set_default_mgmt_key(&rdev->wiphy, netdev, link_id, key_index); ret = rdev->ops->set_default_mgmt_key(&rdev->wiphy, netdev, link_id, key_index); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_default_beacon_key(struct cfg80211_registered_device *rdev, struct net_device *netdev, int link_id, u8 key_index) { int ret; trace_rdev_set_default_beacon_key(&rdev->wiphy, netdev, link_id, key_index); ret = rdev->ops->set_default_beacon_key(&rdev->wiphy, netdev, link_id, key_index); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_start_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ap_settings *settings) { int ret; trace_rdev_start_ap(&rdev->wiphy, dev, settings); ret = rdev->ops->start_ap(&rdev->wiphy, dev, settings); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_beacon(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ap_update *info) { int ret; trace_rdev_change_beacon(&rdev->wiphy, dev, info); ret = rdev->ops->change_beacon(&rdev->wiphy, dev, info); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_stop_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id) { int ret; trace_rdev_stop_ap(&rdev->wiphy, dev, link_id); ret = rdev->ops->stop_ap(&rdev->wiphy, dev, link_id); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_add_station(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *mac, struct station_parameters *params) { int ret; trace_rdev_add_station(&rdev->wiphy, dev, mac, params); ret = rdev->ops->add_station(&rdev->wiphy, dev, mac, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct station_del_parameters *params) { int ret; trace_rdev_del_station(&rdev->wiphy, dev, params); ret = rdev->ops->del_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_station(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *mac, struct station_parameters *params) { int ret; trace_rdev_change_station(&rdev->wiphy, dev, mac, params); ret = rdev->ops->change_station(&rdev->wiphy, dev, mac, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_station(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *mac, struct station_info *sinfo) { int ret; trace_rdev_get_station(&rdev->wiphy, dev, mac); ret = rdev->ops->get_station(&rdev->wiphy, dev, mac, sinfo); trace_rdev_return_int_station_info(&rdev->wiphy, ret, sinfo); return ret; } static inline int rdev_dump_station(struct cfg80211_registered_device *rdev, struct net_device *dev, int idx, u8 *mac, struct station_info *sinfo) { int ret; trace_rdev_dump_station(&rdev->wiphy, dev, idx, mac); ret = rdev->ops->dump_station(&rdev->wiphy, dev, idx, mac, sinfo); trace_rdev_return_int_station_info(&rdev->wiphy, ret, sinfo); return ret; } static inline int rdev_add_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *next_hop) { int ret; trace_rdev_add_mpath(&rdev->wiphy, dev, dst, next_hop); ret = rdev->ops->add_mpath(&rdev->wiphy, dev, dst, next_hop); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst) { int ret; trace_rdev_del_mpath(&rdev->wiphy, dev, dst); ret = rdev->ops->del_mpath(&rdev->wiphy, dev, dst); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *next_hop) { int ret; trace_rdev_change_mpath(&rdev->wiphy, dev, dst, next_hop); ret = rdev->ops->change_mpath(&rdev->wiphy, dev, dst, next_hop); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { int ret; trace_rdev_get_mpath(&rdev->wiphy, dev, dst, next_hop); ret = rdev->ops->get_mpath(&rdev->wiphy, dev, dst, next_hop, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_get_mpp(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { int ret; trace_rdev_get_mpp(&rdev->wiphy, dev, dst, mpp); ret = rdev->ops->get_mpp(&rdev->wiphy, dev, dst, mpp, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_dump_mpath(struct cfg80211_registered_device *rdev, struct net_device *dev, int idx, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { int ret; trace_rdev_dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop); ret = rdev->ops->dump_mpath(&rdev->wiphy, dev, idx, dst, next_hop, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_dump_mpp(struct cfg80211_registered_device *rdev, struct net_device *dev, int idx, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { int ret; trace_rdev_dump_mpp(&rdev->wiphy, dev, idx, dst, mpp); ret = rdev->ops->dump_mpp(&rdev->wiphy, dev, idx, dst, mpp, pinfo); trace_rdev_return_int_mpath_info(&rdev->wiphy, ret, pinfo); return ret; } static inline int rdev_get_mesh_config(struct cfg80211_registered_device *rdev, struct net_device *dev, struct mesh_config *conf) { int ret; trace_rdev_get_mesh_config(&rdev->wiphy, dev); ret = rdev->ops->get_mesh_config(&rdev->wiphy, dev, conf); trace_rdev_return_int_mesh_config(&rdev->wiphy, ret, conf); return ret; } static inline int rdev_update_mesh_config(struct cfg80211_registered_device *rdev, struct net_device *dev, u32 mask, const struct mesh_config *nconf) { int ret; trace_rdev_update_mesh_config(&rdev->wiphy, dev, mask, nconf); ret = rdev->ops->update_mesh_config(&rdev->wiphy, dev, mask, nconf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_join_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev, const struct mesh_config *conf, const struct mesh_setup *setup) { int ret; trace_rdev_join_mesh(&rdev->wiphy, dev, conf, setup); ret = rdev->ops->join_mesh(&rdev->wiphy, dev, conf, setup); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_leave_mesh(struct cfg80211_registered_device *rdev, struct net_device *dev) { int ret; trace_rdev_leave_mesh(&rdev->wiphy, dev); ret = rdev->ops->leave_mesh(&rdev->wiphy, dev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_join_ocb(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ocb_setup *setup) { int ret; trace_rdev_join_ocb(&rdev->wiphy, dev, setup); ret = rdev->ops->join_ocb(&rdev->wiphy, dev, setup); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_leave_ocb(struct cfg80211_registered_device *rdev, struct net_device *dev) { int ret; trace_rdev_leave_ocb(&rdev->wiphy, dev); ret = rdev->ops->leave_ocb(&rdev->wiphy, dev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_change_bss(struct cfg80211_registered_device *rdev, struct net_device *dev, struct bss_parameters *params) { int ret; trace_rdev_change_bss(&rdev->wiphy, dev, params); ret = rdev->ops->change_bss(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_inform_bss(struct cfg80211_registered_device *rdev, struct cfg80211_bss *bss, const struct cfg80211_bss_ies *ies, void *drv_data) { trace_rdev_inform_bss(&rdev->wiphy, bss); if (rdev->ops->inform_bss) rdev->ops->inform_bss(&rdev->wiphy, bss, ies, drv_data); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_set_txq_params(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_txq_params *params) { int ret; trace_rdev_set_txq_params(&rdev->wiphy, dev, params); ret = rdev->ops->set_txq_params(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_libertas_set_mesh_channel(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_channel *chan) { int ret; trace_rdev_libertas_set_mesh_channel(&rdev->wiphy, dev, chan); ret = rdev->ops->libertas_set_mesh_channel(&rdev->wiphy, dev, chan); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_monitor_channel(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_set_monitor_channel(&rdev->wiphy, chandef); ret = rdev->ops->set_monitor_channel(&rdev->wiphy, chandef); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_scan(struct cfg80211_registered_device *rdev, struct cfg80211_scan_request *request) { int ret; if (WARN_ON_ONCE(!request->n_ssids && request->ssids)) return -EINVAL; trace_rdev_scan(&rdev->wiphy, request); ret = rdev->ops->scan(&rdev->wiphy, request); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_abort_scan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_abort_scan(&rdev->wiphy, wdev); rdev->ops->abort_scan(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_auth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_auth_request *req) { int ret; trace_rdev_auth(&rdev->wiphy, dev, req); ret = rdev->ops->auth(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_assoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_assoc_request *req) { int ret; trace_rdev_assoc(&rdev->wiphy, dev, req); ret = rdev->ops->assoc(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_deauth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_deauth_request *req) { int ret; trace_rdev_deauth(&rdev->wiphy, dev, req); ret = rdev->ops->deauth(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_disassoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_disassoc_request *req) { int ret; trace_rdev_disassoc(&rdev->wiphy, dev, req); ret = rdev->ops->disassoc(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_connect(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *sme) { int ret; trace_rdev_connect(&rdev->wiphy, dev, sme); ret = rdev->ops->connect(&rdev->wiphy, dev, sme); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_update_connect_params(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *sme, u32 changed) { int ret; trace_rdev_update_connect_params(&rdev->wiphy, dev, sme, changed); ret = rdev->ops->update_connect_params(&rdev->wiphy, dev, sme, changed); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_disconnect(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 reason_code) { int ret; trace_rdev_disconnect(&rdev->wiphy, dev, reason_code); ret = rdev->ops->disconnect(&rdev->wiphy, dev, reason_code); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_join_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ibss_params *params) { int ret; trace_rdev_join_ibss(&rdev->wiphy, dev, params); ret = rdev->ops->join_ibss(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_leave_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev) { int ret; trace_rdev_leave_ibss(&rdev->wiphy, dev); ret = rdev->ops->leave_ibss(&rdev->wiphy, dev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_wiphy_params(struct cfg80211_registered_device *rdev, u32 changed) { int ret = -EOPNOTSUPP; trace_rdev_set_wiphy_params(&rdev->wiphy, changed); if (rdev->ops->set_wiphy_params) ret = rdev->ops->set_wiphy_params(&rdev->wiphy, changed); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_tx_power(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, enum nl80211_tx_power_setting type, int mbm) { int ret; trace_rdev_set_tx_power(&rdev->wiphy, wdev, type, mbm); ret = rdev->ops->set_tx_power(&rdev->wiphy, wdev, type, mbm); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_tx_power(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, int *dbm) { int ret; trace_rdev_get_tx_power(&rdev->wiphy, wdev); ret = rdev->ops->get_tx_power(&rdev->wiphy, wdev, dbm); trace_rdev_return_int_int(&rdev->wiphy, ret, *dbm); return ret; } static inline int rdev_set_multicast_to_unicast(struct cfg80211_registered_device *rdev, struct net_device *dev, const bool enabled) { int ret; trace_rdev_set_multicast_to_unicast(&rdev->wiphy, dev, enabled); ret = rdev->ops->set_multicast_to_unicast(&rdev->wiphy, dev, enabled); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_txq_stats(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_txq_stats *txqstats) { int ret; trace_rdev_get_txq_stats(&rdev->wiphy, wdev); ret = rdev->ops->get_txq_stats(&rdev->wiphy, wdev, txqstats); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_rfkill_poll(struct cfg80211_registered_device *rdev) { trace_rdev_rfkill_poll(&rdev->wiphy); rdev->ops->rfkill_poll(&rdev->wiphy); trace_rdev_return_void(&rdev->wiphy); } #ifdef CONFIG_NL80211_TESTMODE static inline int rdev_testmode_cmd(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, void *data, int len) { int ret; trace_rdev_testmode_cmd(&rdev->wiphy, wdev); ret = rdev->ops->testmode_cmd(&rdev->wiphy, wdev, data, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_testmode_dump(struct cfg80211_registered_device *rdev, struct sk_buff *skb, struct netlink_callback *cb, void *data, int len) { int ret; trace_rdev_testmode_dump(&rdev->wiphy); ret = rdev->ops->testmode_dump(&rdev->wiphy, skb, cb, data, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } #endif static inline int rdev_set_bitrate_mask(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id, const u8 *peer, const struct cfg80211_bitrate_mask *mask) { int ret; trace_rdev_set_bitrate_mask(&rdev->wiphy, dev, link_id, peer, mask); ret = rdev->ops->set_bitrate_mask(&rdev->wiphy, dev, link_id, peer, mask); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_dump_survey(struct cfg80211_registered_device *rdev, struct net_device *netdev, int idx, struct survey_info *info) { int ret; trace_rdev_dump_survey(&rdev->wiphy, netdev, idx); ret = rdev->ops->dump_survey(&rdev->wiphy, netdev, idx, info); if (ret < 0) trace_rdev_return_int(&rdev->wiphy, ret); else trace_rdev_return_int_survey_info(&rdev->wiphy, ret, info); return ret; } static inline int rdev_set_pmksa(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_pmksa *pmksa) { int ret; trace_rdev_set_pmksa(&rdev->wiphy, netdev, pmksa); ret = rdev->ops->set_pmksa(&rdev->wiphy, netdev, pmksa); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_pmksa(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_pmksa *pmksa) { int ret; trace_rdev_del_pmksa(&rdev->wiphy, netdev, pmksa); ret = rdev->ops->del_pmksa(&rdev->wiphy, netdev, pmksa); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_flush_pmksa(struct cfg80211_registered_device *rdev, struct net_device *netdev) { int ret; trace_rdev_flush_pmksa(&rdev->wiphy, netdev); ret = rdev->ops->flush_pmksa(&rdev->wiphy, netdev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_remain_on_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct ieee80211_channel *chan, unsigned int duration, u64 *cookie) { int ret; trace_rdev_remain_on_channel(&rdev->wiphy, wdev, chan, duration); ret = rdev->ops->remain_on_channel(&rdev->wiphy, wdev, chan, duration, cookie); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } static inline int rdev_cancel_remain_on_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie) { int ret; trace_rdev_cancel_remain_on_channel(&rdev->wiphy, wdev, cookie); ret = rdev->ops->cancel_remain_on_channel(&rdev->wiphy, wdev, cookie); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_mgmt_tx(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_mgmt_tx_params *params, u64 *cookie) { int ret; trace_rdev_mgmt_tx(&rdev->wiphy, wdev, params); ret = rdev->ops->mgmt_tx(&rdev->wiphy, wdev, params, cookie); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } static inline int rdev_tx_control_port(struct cfg80211_registered_device *rdev, struct net_device *dev, const void *buf, size_t len, const u8 *dest, __be16 proto, const bool noencrypt, int link, u64 *cookie) { int ret; trace_rdev_tx_control_port(&rdev->wiphy, dev, buf, len, dest, proto, noencrypt, link); ret = rdev->ops->tx_control_port(&rdev->wiphy, dev, buf, len, dest, proto, noencrypt, link, cookie); if (cookie) trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); else trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_mgmt_tx_cancel_wait(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie) { int ret; trace_rdev_mgmt_tx_cancel_wait(&rdev->wiphy, wdev, cookie); ret = rdev->ops->mgmt_tx_cancel_wait(&rdev->wiphy, wdev, cookie); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_power_mgmt(struct cfg80211_registered_device *rdev, struct net_device *dev, bool enabled, int timeout) { int ret; trace_rdev_set_power_mgmt(&rdev->wiphy, dev, enabled, timeout); ret = rdev->ops->set_power_mgmt(&rdev->wiphy, dev, enabled, timeout); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_cqm_rssi_config(struct cfg80211_registered_device *rdev, struct net_device *dev, s32 rssi_thold, u32 rssi_hyst) { int ret; trace_rdev_set_cqm_rssi_config(&rdev->wiphy, dev, rssi_thold, rssi_hyst); ret = rdev->ops->set_cqm_rssi_config(&rdev->wiphy, dev, rssi_thold, rssi_hyst); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_cqm_rssi_range_config(struct cfg80211_registered_device *rdev, struct net_device *dev, s32 low, s32 high) { int ret; trace_rdev_set_cqm_rssi_range_config(&rdev->wiphy, dev, low, high); ret = rdev->ops->set_cqm_rssi_range_config(&rdev->wiphy, dev, low, high); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_cqm_txe_config(struct cfg80211_registered_device *rdev, struct net_device *dev, u32 rate, u32 pkts, u32 intvl) { int ret; trace_rdev_set_cqm_txe_config(&rdev->wiphy, dev, rate, pkts, intvl); ret = rdev->ops->set_cqm_txe_config(&rdev->wiphy, dev, rate, pkts, intvl); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_update_mgmt_frame_registrations(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct mgmt_frame_regs *upd) { might_sleep(); trace_rdev_update_mgmt_frame_registrations(&rdev->wiphy, wdev, upd); if (rdev->ops->update_mgmt_frame_registrations) rdev->ops->update_mgmt_frame_registrations(&rdev->wiphy, wdev, upd); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_set_antenna(struct cfg80211_registered_device *rdev, u32 tx_ant, u32 rx_ant) { int ret; trace_rdev_set_antenna(&rdev->wiphy, tx_ant, rx_ant); ret = rdev->ops->set_antenna(&rdev->wiphy, tx_ant, rx_ant); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_antenna(struct cfg80211_registered_device *rdev, u32 *tx_ant, u32 *rx_ant) { int ret; trace_rdev_get_antenna(&rdev->wiphy); ret = rdev->ops->get_antenna(&rdev->wiphy, tx_ant, rx_ant); if (ret) trace_rdev_return_int(&rdev->wiphy, ret); else trace_rdev_return_int_tx_rx(&rdev->wiphy, ret, *tx_ant, *rx_ant); return ret; } static inline int rdev_sched_scan_start(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_sched_scan_request *request) { int ret; trace_rdev_sched_scan_start(&rdev->wiphy, dev, request->reqid); ret = rdev->ops->sched_scan_start(&rdev->wiphy, dev, request); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_sched_scan_stop(struct cfg80211_registered_device *rdev, struct net_device *dev, u64 reqid) { int ret; trace_rdev_sched_scan_stop(&rdev->wiphy, dev, reqid); ret = rdev->ops->sched_scan_stop(&rdev->wiphy, dev, reqid); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_rekey_data(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_gtk_rekey_data *data) { int ret; trace_rdev_set_rekey_data(&rdev->wiphy, dev); ret = rdev->ops->set_rekey_data(&rdev->wiphy, dev, data); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_tdls_mgmt(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *peer, int link_id, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, bool initiator, const u8 *buf, size_t len) { int ret; trace_rdev_tdls_mgmt(&rdev->wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, buf, len); ret = rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, link_id, action_code, dialog_token, status_code, peer_capability, initiator, buf, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_tdls_oper(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *peer, enum nl80211_tdls_operation oper) { int ret; trace_rdev_tdls_oper(&rdev->wiphy, dev, peer, oper); ret = rdev->ops->tdls_oper(&rdev->wiphy, dev, peer, oper); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_probe_client(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *peer, u64 *cookie) { int ret; trace_rdev_probe_client(&rdev->wiphy, dev, peer); ret = rdev->ops->probe_client(&rdev->wiphy, dev, peer, cookie); trace_rdev_return_int_cookie(&rdev->wiphy, ret, *cookie); return ret; } static inline int rdev_set_noack_map(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 noack_map) { int ret; trace_rdev_set_noack_map(&rdev->wiphy, dev, noack_map); ret = rdev->ops->set_noack_map(&rdev->wiphy, dev, noack_map); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_channel(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, unsigned int link_id, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_get_channel(&rdev->wiphy, wdev, link_id); ret = rdev->ops->get_channel(&rdev->wiphy, wdev, link_id, chandef); trace_rdev_return_chandef(&rdev->wiphy, ret, chandef); return ret; } static inline int rdev_start_p2p_device(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { int ret; trace_rdev_start_p2p_device(&rdev->wiphy, wdev); ret = rdev->ops->start_p2p_device(&rdev->wiphy, wdev); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_stop_p2p_device(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_stop_p2p_device(&rdev->wiphy, wdev); rdev->ops->stop_p2p_device(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_start_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf) { int ret; trace_rdev_start_nan(&rdev->wiphy, wdev, conf); ret = rdev->ops->start_nan(&rdev->wiphy, wdev, conf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_stop_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_stop_nan(&rdev->wiphy, wdev); rdev->ops->stop_nan(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_add_nan_func(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_nan_func *nan_func) { int ret; trace_rdev_add_nan_func(&rdev->wiphy, wdev, nan_func); ret = rdev->ops->add_nan_func(&rdev->wiphy, wdev, nan_func); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_del_nan_func(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u64 cookie) { trace_rdev_del_nan_func(&rdev->wiphy, wdev, cookie); rdev->ops->del_nan_func(&rdev->wiphy, wdev, cookie); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_nan_change_conf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf, u32 changes) { int ret; trace_rdev_nan_change_conf(&rdev->wiphy, wdev, conf, changes); if (rdev->ops->nan_change_conf) ret = rdev->ops->nan_change_conf(&rdev->wiphy, wdev, conf, changes); else ret = -EOPNOTSUPP; trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_mac_acl(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_acl_data *params) { int ret; trace_rdev_set_mac_acl(&rdev->wiphy, dev, params); ret = rdev->ops->set_mac_acl(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_update_ft_ies(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_update_ft_ies_params *ftie) { int ret; trace_rdev_update_ft_ies(&rdev->wiphy, dev, ftie); ret = rdev->ops->update_ft_ies(&rdev->wiphy, dev, ftie); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_crit_proto_start(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, enum nl80211_crit_proto_id protocol, u16 duration) { int ret; trace_rdev_crit_proto_start(&rdev->wiphy, wdev, protocol, duration); ret = rdev->ops->crit_proto_start(&rdev->wiphy, wdev, protocol, duration); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_crit_proto_stop(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { trace_rdev_crit_proto_stop(&rdev->wiphy, wdev); rdev->ops->crit_proto_stop(&rdev->wiphy, wdev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_channel_switch(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_csa_settings *params) { int ret; trace_rdev_channel_switch(&rdev->wiphy, dev, params); ret = rdev->ops->channel_switch(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_qos_map(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_qos_map *qos_map) { int ret = -EOPNOTSUPP; if (rdev->ops->set_qos_map) { trace_rdev_set_qos_map(&rdev->wiphy, dev, qos_map); ret = rdev->ops->set_qos_map(&rdev->wiphy, dev, qos_map); trace_rdev_return_int(&rdev->wiphy, ret); } return ret; } static inline int rdev_set_ap_chanwidth(struct cfg80211_registered_device *rdev, struct net_device *dev, unsigned int link_id, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_set_ap_chanwidth(&rdev->wiphy, dev, link_id, chandef); ret = rdev->ops->set_ap_chanwidth(&rdev->wiphy, dev, link_id, chandef); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_add_tx_ts(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 tsid, const u8 *peer, u8 user_prio, u16 admitted_time) { int ret = -EOPNOTSUPP; trace_rdev_add_tx_ts(&rdev->wiphy, dev, tsid, peer, user_prio, admitted_time); if (rdev->ops->add_tx_ts) ret = rdev->ops->add_tx_ts(&rdev->wiphy, dev, tsid, peer, user_prio, admitted_time); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_tx_ts(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 tsid, const u8 *peer) { int ret = -EOPNOTSUPP; trace_rdev_del_tx_ts(&rdev->wiphy, dev, tsid, peer); if (rdev->ops->del_tx_ts) ret = rdev->ops->del_tx_ts(&rdev->wiphy, dev, tsid, peer); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_tdls_channel_switch(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *addr, u8 oper_class, struct cfg80211_chan_def *chandef) { int ret; trace_rdev_tdls_channel_switch(&rdev->wiphy, dev, addr, oper_class, chandef); ret = rdev->ops->tdls_channel_switch(&rdev->wiphy, dev, addr, oper_class, chandef); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_tdls_cancel_channel_switch(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *addr) { trace_rdev_tdls_cancel_channel_switch(&rdev->wiphy, dev, addr); rdev->ops->tdls_cancel_channel_switch(&rdev->wiphy, dev, addr); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_start_radar_detection(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_chan_def *chandef, u32 cac_time_ms) { int ret = -EOPNOTSUPP; trace_rdev_start_radar_detection(&rdev->wiphy, dev, chandef, cac_time_ms); if (rdev->ops->start_radar_detection) ret = rdev->ops->start_radar_detection(&rdev->wiphy, dev, chandef, cac_time_ms); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_end_cac(struct cfg80211_registered_device *rdev, struct net_device *dev) { trace_rdev_end_cac(&rdev->wiphy, dev); if (rdev->ops->end_cac) rdev->ops->end_cac(&rdev->wiphy, dev); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_set_mcast_rate(struct cfg80211_registered_device *rdev, struct net_device *dev, int mcast_rate[NUM_NL80211_BANDS]) { int ret = -EOPNOTSUPP; trace_rdev_set_mcast_rate(&rdev->wiphy, dev, mcast_rate); if (rdev->ops->set_mcast_rate) ret = rdev->ops->set_mcast_rate(&rdev->wiphy, dev, mcast_rate); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_coalesce(struct cfg80211_registered_device *rdev, struct cfg80211_coalesce *coalesce) { int ret = -EOPNOTSUPP; trace_rdev_set_coalesce(&rdev->wiphy, coalesce); if (rdev->ops->set_coalesce) ret = rdev->ops->set_coalesce(&rdev->wiphy, coalesce); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_pmk(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_pmk_conf *pmk_conf) { int ret = -EOPNOTSUPP; trace_rdev_set_pmk(&rdev->wiphy, dev, pmk_conf); if (rdev->ops->set_pmk) ret = rdev->ops->set_pmk(&rdev->wiphy, dev, pmk_conf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_pmk(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *aa) { int ret = -EOPNOTSUPP; trace_rdev_del_pmk(&rdev->wiphy, dev, aa); if (rdev->ops->del_pmk) ret = rdev->ops->del_pmk(&rdev->wiphy, dev, aa); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_external_auth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_external_auth_params *params) { int ret = -EOPNOTSUPP; trace_rdev_external_auth(&rdev->wiphy, dev, params); if (rdev->ops->external_auth) ret = rdev->ops->external_auth(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_get_ftm_responder_stats(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ftm_responder_stats *ftm_stats) { int ret = -EOPNOTSUPP; trace_rdev_get_ftm_responder_stats(&rdev->wiphy, dev, ftm_stats); if (rdev->ops->get_ftm_responder_stats) ret = rdev->ops->get_ftm_responder_stats(&rdev->wiphy, dev, ftm_stats); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_start_pmsr(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_pmsr_request *request) { int ret = -EOPNOTSUPP; trace_rdev_start_pmsr(&rdev->wiphy, wdev, request->cookie); if (rdev->ops->start_pmsr) ret = rdev->ops->start_pmsr(&rdev->wiphy, wdev, request); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_abort_pmsr(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_pmsr_request *request) { trace_rdev_abort_pmsr(&rdev->wiphy, wdev, request->cookie); if (rdev->ops->abort_pmsr) rdev->ops->abort_pmsr(&rdev->wiphy, wdev, request); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_update_owe_info(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_update_owe_info *oweinfo) { int ret = -EOPNOTSUPP; trace_rdev_update_owe_info(&rdev->wiphy, dev, oweinfo); if (rdev->ops->update_owe_info) ret = rdev->ops->update_owe_info(&rdev->wiphy, dev, oweinfo); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_probe_mesh_link(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *dest, const void *buf, size_t len) { int ret; trace_rdev_probe_mesh_link(&rdev->wiphy, dev, dest, buf, len); ret = rdev->ops->probe_mesh_link(&rdev->wiphy, dev, buf, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_tid_config(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_tid_config *tid_conf) { int ret; trace_rdev_set_tid_config(&rdev->wiphy, dev, tid_conf); ret = rdev->ops->set_tid_config(&rdev->wiphy, dev, tid_conf); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_reset_tid_config(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *peer, u8 tids) { int ret; trace_rdev_reset_tid_config(&rdev->wiphy, dev, peer, tids); ret = rdev->ops->reset_tid_config(&rdev->wiphy, dev, peer, tids); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_sar_specs(struct cfg80211_registered_device *rdev, struct cfg80211_sar_specs *sar) { int ret; trace_rdev_set_sar_specs(&rdev->wiphy, sar); ret = rdev->ops->set_sar_specs(&rdev->wiphy, sar); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_color_change(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_color_change_settings *params) { int ret; trace_rdev_color_change(&rdev->wiphy, dev, params); ret = rdev->ops->color_change(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_fils_aad(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_fils_aad *fils_aad) { int ret = -EOPNOTSUPP; trace_rdev_set_fils_aad(&rdev->wiphy, dev, fils_aad); if (rdev->ops->set_fils_aad) ret = rdev->ops->set_fils_aad(&rdev->wiphy, dev, fils_aad); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_radar_background(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_radar_background(wiphy, chandef); if (rdev->ops->set_radar_background) ret = rdev->ops->set_radar_background(wiphy, chandef); trace_rdev_return_int(wiphy, ret); return ret; } static inline int rdev_add_intf_link(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, unsigned int link_id) { int ret = 0; trace_rdev_add_intf_link(&rdev->wiphy, wdev, link_id); if (rdev->ops->add_intf_link) ret = rdev->ops->add_intf_link(&rdev->wiphy, wdev, link_id); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_del_intf_link(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, unsigned int link_id) { trace_rdev_del_intf_link(&rdev->wiphy, wdev, link_id); if (rdev->ops->del_intf_link) rdev->ops->del_intf_link(&rdev->wiphy, wdev, link_id); trace_rdev_return_void(&rdev->wiphy); } static inline int rdev_add_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_parameters *params) { int ret = -EOPNOTSUPP; trace_rdev_add_link_station(&rdev->wiphy, dev, params); if (rdev->ops->add_link_station) ret = rdev->ops->add_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_mod_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_parameters *params) { int ret = -EOPNOTSUPP; trace_rdev_mod_link_station(&rdev->wiphy, dev, params); if (rdev->ops->mod_link_station) ret = rdev->ops->mod_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_del_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_del_parameters *params) { int ret = -EOPNOTSUPP; trace_rdev_del_link_station(&rdev->wiphy, dev, params); if (rdev->ops->del_link_station) ret = rdev->ops->del_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline int rdev_set_hw_timestamp(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_set_hw_timestamp *hwts) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_hw_timestamp(wiphy, dev, hwts); if (rdev->ops->set_hw_timestamp) ret = rdev->ops->set_hw_timestamp(wiphy, dev, hwts); trace_rdev_return_int(wiphy, ret); return ret; } static inline int rdev_set_ttlm(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ttlm_params *params) { struct wiphy *wiphy = &rdev->wiphy; int ret = -EOPNOTSUPP; trace_rdev_set_ttlm(wiphy, dev, params); if (rdev->ops->set_ttlm) ret = rdev->ops->set_ttlm(wiphy, dev, params); trace_rdev_return_int(wiphy, ret); return ret; } static inline u32 rdev_get_radio_mask(struct cfg80211_registered_device *rdev, struct net_device *dev) { struct wiphy *wiphy = &rdev->wiphy; if (!rdev->ops->get_radio_mask) return 0; return rdev->ops->get_radio_mask(wiphy, dev); } #endif /* __CFG80211_RDEV_OPS */ |
| 32 31 31 29 29 29 29 31 31 29 29 29 29 29 29 29 29 31 30 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_FORMAT_H #define _BCACHEFS_FORMAT_H /* * bcachefs on disk data structures * * OVERVIEW: * * There are three main types of on disk data structures in bcachefs (this is * reduced from 5 in bcache) * * - superblock * - journal * - btree * * The btree is the primary structure; most metadata exists as keys in the * various btrees. There are only a small number of btrees, they're not * sharded - we have one btree for extents, another for inodes, et cetera. * * SUPERBLOCK: * * The superblock contains the location of the journal, the list of devices in * the filesystem, and in general any metadata we need in order to decide * whether we can start a filesystem or prior to reading the journal/btree * roots. * * The superblock is extensible, and most of the contents of the superblock are * in variable length, type tagged fields; see struct bch_sb_field. * * Backup superblocks do not reside in a fixed location; also, superblocks do * not have a fixed size. To locate backup superblocks we have struct * bch_sb_layout; we store a copy of this inside every superblock, and also * before the first superblock. * * JOURNAL: * * The journal primarily records btree updates in the order they occurred; * journal replay consists of just iterating over all the keys in the open * journal entries and re-inserting them into the btrees. * * The journal also contains entry types for the btree roots, and blacklisted * journal sequence numbers (see journal_seq_blacklist.c). * * BTREE: * * bcachefs btrees are copy on write b+ trees, where nodes are big (typically * 128k-256k) and log structured. We use struct btree_node for writing the first * entry in a given node (offset 0), and struct btree_node_entry for all * subsequent writes. * * After the header, btree node entries contain a list of keys in sorted order. * Values are stored inline with the keys; since values are variable length (and * keys effectively are variable length too, due to packing) we can't do random * access without building up additional in memory tables in the btree node read * path. * * BTREE KEYS (struct bkey): * * The various btrees share a common format for the key - so as to avoid * switching in fastpath lookup/comparison code - but define their own * structures for the key values. * * The size of a key/value pair is stored as a u8 in units of u64s, so the max * size is just under 2k. The common part also contains a type tag for the * value, and a format field indicating whether the key is packed or not (and * also meant to allow adding new key fields in the future, if desired). * * bkeys, when stored within a btree node, may also be packed. In that case, the * bkey_format in that node is used to unpack it. Packed bkeys mean that we can * be generous with field sizes in the common part of the key format (64 bit * inode number, 64 bit offset, 96 bit version field, etc.) for negligible cost. */ #include <asm/types.h> #include <asm/byteorder.h> #include <linux/kernel.h> #include <linux/uuid.h> #include <uapi/linux/magic.h> #include "vstructs.h" #ifdef __KERNEL__ typedef uuid_t __uuid_t; #endif #define BITMASK(name, type, field, offset, end) \ static const __maybe_unused unsigned name##_OFFSET = offset; \ static const __maybe_unused unsigned name##_BITS = (end - offset); \ \ static inline __u64 name(const type *k) \ { \ return (k->field >> offset) & ~(~0ULL << (end - offset)); \ } \ \ static inline void SET_##name(type *k, __u64 v) \ { \ k->field &= ~(~(~0ULL << (end - offset)) << offset); \ k->field |= (v & ~(~0ULL << (end - offset))) << offset; \ } #define LE_BITMASK(_bits, name, type, field, offset, end) \ static const __maybe_unused unsigned name##_OFFSET = offset; \ static const __maybe_unused unsigned name##_BITS = (end - offset); \ static const __maybe_unused __u##_bits name##_MAX = (1ULL << (end - offset)) - 1;\ \ static inline __u64 name(const type *k) \ { \ return (__le##_bits##_to_cpu(k->field) >> offset) & \ ~(~0ULL << (end - offset)); \ } \ \ static inline void SET_##name(type *k, __u64 v) \ { \ __u##_bits new = __le##_bits##_to_cpu(k->field); \ \ new &= ~(~(~0ULL << (end - offset)) << offset); \ new |= (v & ~(~0ULL << (end - offset))) << offset; \ k->field = __cpu_to_le##_bits(new); \ } #define LE16_BITMASK(n, t, f, o, e) LE_BITMASK(16, n, t, f, o, e) #define LE32_BITMASK(n, t, f, o, e) LE_BITMASK(32, n, t, f, o, e) #define LE64_BITMASK(n, t, f, o, e) LE_BITMASK(64, n, t, f, o, e) struct bkey_format { __u8 key_u64s; __u8 nr_fields; /* One unused slot for now: */ __u8 bits_per_field[6]; __le64 field_offset[6]; }; /* Btree keys - all units are in sectors */ struct bpos { /* * Word order matches machine byte order - btree code treats a bpos as a * single large integer, for search/comparison purposes * * Note that wherever a bpos is embedded in another on disk data * structure, it has to be byte swabbed when reading in metadata that * wasn't written in native endian order: */ #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ __u32 snapshot; __u64 offset; __u64 inode; #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ __u64 inode; __u64 offset; /* Points to end of extent - sectors */ __u32 snapshot; #else #error edit for your odd byteorder. #endif } __packed #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ __aligned(4) #endif ; #define KEY_INODE_MAX ((__u64)~0ULL) #define KEY_OFFSET_MAX ((__u64)~0ULL) #define KEY_SNAPSHOT_MAX ((__u32)~0U) #define KEY_SIZE_MAX ((__u32)~0U) static inline struct bpos SPOS(__u64 inode, __u64 offset, __u32 snapshot) { return (struct bpos) { .inode = inode, .offset = offset, .snapshot = snapshot, }; } #define POS_MIN SPOS(0, 0, 0) #define POS_MAX SPOS(KEY_INODE_MAX, KEY_OFFSET_MAX, 0) #define SPOS_MAX SPOS(KEY_INODE_MAX, KEY_OFFSET_MAX, KEY_SNAPSHOT_MAX) #define POS(_inode, _offset) SPOS(_inode, _offset, 0) /* Empty placeholder struct, for container_of() */ struct bch_val { __u64 __nothing[0]; }; struct bversion { #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ __u64 lo; __u32 hi; #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ __u32 hi; __u64 lo; #endif } __packed #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ __aligned(4) #endif ; struct bkey { /* Size of combined key and value, in u64s */ __u8 u64s; /* Format of key (0 for format local to btree node) */ #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 format:7, needs_whiteout:1; #elif defined (__BIG_ENDIAN_BITFIELD) __u8 needs_whiteout:1, format:7; #else #error edit for your odd byteorder. #endif /* Type of the value */ __u8 type; #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ __u8 pad[1]; struct bversion version; __u32 size; /* extent size, in sectors */ struct bpos p; #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ struct bpos p; __u32 size; /* extent size, in sectors */ struct bversion version; __u8 pad[1]; #endif } __packed #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ /* * The big-endian version of bkey can't be compiled by rustc with the "aligned" * attr since it doesn't allow types to have both "packed" and "aligned" attrs. * So for Rust compatibility, don't include this. It can be included in the LE * version because the "packed" attr is redundant in that case. * * History: (quoting Kent) * * Specifically, when i was designing bkey, I wanted the header to be no * bigger than necessary so that bkey_packed could use the rest. That means that * decently offten extent keys will fit into only 8 bytes, instead of spilling over * to 16. * * But packed_bkey treats the part after the header - the packed section - * as a single multi word, variable length integer. And bkey, the unpacked * version, is just a special case version of a bkey_packed; all the packed * bkey code will work on keys in any packed format, the in-memory * representation of an unpacked key also is just one type of packed key... * * So that constrains the key part of a bkig endian bkey to start right * after the header. * * If we ever do a bkey_v2 and need to expand the hedaer by another byte for * some reason - that will clean up this wart. */ __aligned(8) #endif ; struct bkey_packed { __u64 _data[0]; /* Size of combined key and value, in u64s */ __u8 u64s; /* Format of key (0 for format local to btree node) */ /* * XXX: next incompat on disk format change, switch format and * needs_whiteout - bkey_packed() will be cheaper if format is the high * bits of the bitfield */ #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 format:7, needs_whiteout:1; #elif defined (__BIG_ENDIAN_BITFIELD) __u8 needs_whiteout:1, format:7; #endif /* Type of the value */ __u8 type; __u8 key_start[0]; /* * We copy bkeys with struct assignment in various places, and while * that shouldn't be done with packed bkeys we can't disallow it in C, * and it's legal to cast a bkey to a bkey_packed - so padding it out * to the same size as struct bkey should hopefully be safest. */ __u8 pad[sizeof(struct bkey) - 3]; } __packed __aligned(8); typedef struct { __le64 lo; __le64 hi; } bch_le128; #define BKEY_U64s (sizeof(struct bkey) / sizeof(__u64)) #define BKEY_U64s_MAX U8_MAX #define BKEY_VAL_U64s_MAX (BKEY_U64s_MAX - BKEY_U64s) #define KEY_PACKED_BITS_START 24 #define KEY_FORMAT_LOCAL_BTREE 0 #define KEY_FORMAT_CURRENT 1 enum bch_bkey_fields { BKEY_FIELD_INODE, BKEY_FIELD_OFFSET, BKEY_FIELD_SNAPSHOT, BKEY_FIELD_SIZE, BKEY_FIELD_VERSION_HI, BKEY_FIELD_VERSION_LO, BKEY_NR_FIELDS, }; #define bkey_format_field(name, field) \ [BKEY_FIELD_##name] = (sizeof(((struct bkey *) NULL)->field) * 8) #define BKEY_FORMAT_CURRENT \ ((struct bkey_format) { \ .key_u64s = BKEY_U64s, \ .nr_fields = BKEY_NR_FIELDS, \ .bits_per_field = { \ bkey_format_field(INODE, p.inode), \ bkey_format_field(OFFSET, p.offset), \ bkey_format_field(SNAPSHOT, p.snapshot), \ bkey_format_field(SIZE, size), \ bkey_format_field(VERSION_HI, version.hi), \ bkey_format_field(VERSION_LO, version.lo), \ }, \ }) /* bkey with inline value */ struct bkey_i { __u64 _data[0]; struct bkey k; struct bch_val v; }; #define POS_KEY(_pos) \ ((struct bkey) { \ .u64s = BKEY_U64s, \ .format = KEY_FORMAT_CURRENT, \ .p = _pos, \ }) #define KEY(_inode, _offset, _size) \ ((struct bkey) { \ .u64s = BKEY_U64s, \ .format = KEY_FORMAT_CURRENT, \ .p = POS(_inode, _offset), \ .size = _size, \ }) static inline void bkey_init(struct bkey *k) { *k = KEY(0, 0, 0); } #define bkey_bytes(_k) ((_k)->u64s * sizeof(__u64)) #define __BKEY_PADDED(key, pad) \ struct bkey_i key; __u64 key ## _pad[pad] /* * - DELETED keys are used internally to mark keys that should be ignored but * override keys in composition order. Their version number is ignored. * * - DISCARDED keys indicate that the data is all 0s because it has been * discarded. DISCARDs may have a version; if the version is nonzero the key * will be persistent, otherwise the key will be dropped whenever the btree * node is rewritten (like DELETED keys). * * - ERROR: any read of the data returns a read error, as the data was lost due * to a failing device. Like DISCARDED keys, they can be removed (overridden) * by new writes or cluster-wide GC. Node repair can also overwrite them with * the same or a more recent version number, but not with an older version * number. * * - WHITEOUT: for hash table btrees */ #define BCH_BKEY_TYPES() \ x(deleted, 0) \ x(whiteout, 1) \ x(error, 2) \ x(cookie, 3) \ x(hash_whiteout, 4) \ x(btree_ptr, 5) \ x(extent, 6) \ x(reservation, 7) \ x(inode, 8) \ x(inode_generation, 9) \ x(dirent, 10) \ x(xattr, 11) \ x(alloc, 12) \ x(quota, 13) \ x(stripe, 14) \ x(reflink_p, 15) \ x(reflink_v, 16) \ x(inline_data, 17) \ x(btree_ptr_v2, 18) \ x(indirect_inline_data, 19) \ x(alloc_v2, 20) \ x(subvolume, 21) \ x(snapshot, 22) \ x(inode_v2, 23) \ x(alloc_v3, 24) \ x(set, 25) \ x(lru, 26) \ x(alloc_v4, 27) \ x(backpointer, 28) \ x(inode_v3, 29) \ x(bucket_gens, 30) \ x(snapshot_tree, 31) \ x(logged_op_truncate, 32) \ x(logged_op_finsert, 33) \ x(accounting, 34) enum bch_bkey_type { #define x(name, nr) KEY_TYPE_##name = nr, BCH_BKEY_TYPES() #undef x KEY_TYPE_MAX, }; struct bch_deleted { struct bch_val v; }; struct bch_whiteout { struct bch_val v; }; struct bch_error { struct bch_val v; }; struct bch_cookie { struct bch_val v; __le64 cookie; }; struct bch_hash_whiteout { struct bch_val v; }; struct bch_set { struct bch_val v; }; /* 128 bits, sufficient for cryptographic MACs: */ struct bch_csum { __le64 lo; __le64 hi; } __packed __aligned(8); struct bch_backpointer { struct bch_val v; __u8 btree_id; __u8 level; __u8 data_type; __u64 bucket_offset:40; __u32 bucket_len; struct bpos pos; } __packed __aligned(8); /* Optional/variable size superblock sections: */ struct bch_sb_field { __u64 _data[0]; __le32 u64s; __le32 type; }; #define BCH_SB_FIELDS() \ x(journal, 0) \ x(members_v1, 1) \ x(crypt, 2) \ x(replicas_v0, 3) \ x(quota, 4) \ x(disk_groups, 5) \ x(clean, 6) \ x(replicas, 7) \ x(journal_seq_blacklist, 8) \ x(journal_v2, 9) \ x(counters, 10) \ x(members_v2, 11) \ x(errors, 12) \ x(ext, 13) \ x(downgrade, 14) #include "alloc_background_format.h" #include "dirent_format.h" #include "disk_accounting_format.h" #include "disk_groups_format.h" #include "extents_format.h" #include "ec_format.h" #include "dirent_format.h" #include "disk_groups_format.h" #include "inode_format.h" #include "journal_seq_blacklist_format.h" #include "logged_ops_format.h" #include "lru_format.h" #include "quota_format.h" #include "reflink_format.h" #include "replicas_format.h" #include "snapshot_format.h" #include "subvolume_format.h" #include "sb-counters_format.h" #include "sb-downgrade_format.h" #include "sb-errors_format.h" #include "sb-members_format.h" #include "xattr_format.h" enum bch_sb_field_type { #define x(f, nr) BCH_SB_FIELD_##f = nr, BCH_SB_FIELDS() #undef x BCH_SB_FIELD_NR }; /* * Most superblock fields are replicated in all device's superblocks - a few are * not: */ #define BCH_SINGLE_DEVICE_SB_FIELDS \ ((1U << BCH_SB_FIELD_journal)| \ (1U << BCH_SB_FIELD_journal_v2)) /* BCH_SB_FIELD_journal: */ struct bch_sb_field_journal { struct bch_sb_field field; __le64 buckets[]; }; struct bch_sb_field_journal_v2 { struct bch_sb_field field; struct bch_sb_field_journal_v2_entry { __le64 start; __le64 nr; } d[]; }; /* BCH_SB_FIELD_crypt: */ struct nonce { __le32 d[4]; }; struct bch_key { __le64 key[4]; }; #define BCH_KEY_MAGIC \ (((__u64) 'b' << 0)|((__u64) 'c' << 8)| \ ((__u64) 'h' << 16)|((__u64) '*' << 24)| \ ((__u64) '*' << 32)|((__u64) 'k' << 40)| \ ((__u64) 'e' << 48)|((__u64) 'y' << 56)) struct bch_encrypted_key { __le64 magic; struct bch_key key; }; /* * If this field is present in the superblock, it stores an encryption key which * is used encrypt all other data/metadata. The key will normally be encrypted * with the key userspace provides, but if encryption has been turned off we'll * just store the master key unencrypted in the superblock so we can access the * previously encrypted data. */ struct bch_sb_field_crypt { struct bch_sb_field field; __le64 flags; __le64 kdf_flags; struct bch_encrypted_key key; }; LE64_BITMASK(BCH_CRYPT_KDF_TYPE, struct bch_sb_field_crypt, flags, 0, 4); enum bch_kdf_types { BCH_KDF_SCRYPT = 0, BCH_KDF_NR = 1, }; /* stored as base 2 log of scrypt params: */ LE64_BITMASK(BCH_KDF_SCRYPT_N, struct bch_sb_field_crypt, kdf_flags, 0, 16); LE64_BITMASK(BCH_KDF_SCRYPT_R, struct bch_sb_field_crypt, kdf_flags, 16, 32); LE64_BITMASK(BCH_KDF_SCRYPT_P, struct bch_sb_field_crypt, kdf_flags, 32, 48); /* * On clean shutdown, store btree roots and current journal sequence number in * the superblock: */ struct jset_entry { __le16 u64s; __u8 btree_id; __u8 level; __u8 type; /* designates what this jset holds */ __u8 pad[3]; struct bkey_i start[0]; __u64 _data[]; }; struct bch_sb_field_clean { struct bch_sb_field field; __le32 flags; __le16 _read_clock; /* no longer used */ __le16 _write_clock; __le64 journal_seq; struct jset_entry start[0]; __u64 _data[]; }; struct bch_sb_field_ext { struct bch_sb_field field; __le64 recovery_passes_required[2]; __le64 errors_silent[8]; __le64 btrees_lost_data; }; /* Superblock: */ /* * New versioning scheme: * One common version number for all on disk data structures - superblock, btree * nodes, journal entries */ #define BCH_VERSION_MAJOR(_v) ((__u16) ((_v) >> 10)) #define BCH_VERSION_MINOR(_v) ((__u16) ((_v) & ~(~0U << 10))) #define BCH_VERSION(_major, _minor) (((_major) << 10)|(_minor) << 0) /* * field 1: version name * field 2: BCH_VERSION(major, minor) * field 3: recovery passess required on upgrade */ #define BCH_METADATA_VERSIONS() \ x(bkey_renumber, BCH_VERSION(0, 10)) \ x(inode_btree_change, BCH_VERSION(0, 11)) \ x(snapshot, BCH_VERSION(0, 12)) \ x(inode_backpointers, BCH_VERSION(0, 13)) \ x(btree_ptr_sectors_written, BCH_VERSION(0, 14)) \ x(snapshot_2, BCH_VERSION(0, 15)) \ x(reflink_p_fix, BCH_VERSION(0, 16)) \ x(subvol_dirent, BCH_VERSION(0, 17)) \ x(inode_v2, BCH_VERSION(0, 18)) \ x(freespace, BCH_VERSION(0, 19)) \ x(alloc_v4, BCH_VERSION(0, 20)) \ x(new_data_types, BCH_VERSION(0, 21)) \ x(backpointers, BCH_VERSION(0, 22)) \ x(inode_v3, BCH_VERSION(0, 23)) \ x(unwritten_extents, BCH_VERSION(0, 24)) \ x(bucket_gens, BCH_VERSION(0, 25)) \ x(lru_v2, BCH_VERSION(0, 26)) \ x(fragmentation_lru, BCH_VERSION(0, 27)) \ x(no_bps_in_alloc_keys, BCH_VERSION(0, 28)) \ x(snapshot_trees, BCH_VERSION(0, 29)) \ x(major_minor, BCH_VERSION(1, 0)) \ x(snapshot_skiplists, BCH_VERSION(1, 1)) \ x(deleted_inodes, BCH_VERSION(1, 2)) \ x(rebalance_work, BCH_VERSION(1, 3)) \ x(member_seq, BCH_VERSION(1, 4)) \ x(subvolume_fs_parent, BCH_VERSION(1, 5)) \ x(btree_subvolume_children, BCH_VERSION(1, 6)) \ x(mi_btree_bitmap, BCH_VERSION(1, 7)) \ x(bucket_stripe_sectors, BCH_VERSION(1, 8)) \ x(disk_accounting_v2, BCH_VERSION(1, 9)) enum bcachefs_metadata_version { bcachefs_metadata_version_min = 9, #define x(t, n) bcachefs_metadata_version_##t = n, BCH_METADATA_VERSIONS() #undef x bcachefs_metadata_version_max }; static const __maybe_unused unsigned bcachefs_metadata_required_upgrade_below = bcachefs_metadata_version_rebalance_work; #define bcachefs_metadata_version_current (bcachefs_metadata_version_max - 1) #define BCH_SB_SECTOR 8 #define BCH_SB_LAYOUT_SIZE_BITS_MAX 16 /* 32 MB */ struct bch_sb_layout { __uuid_t magic; /* bcachefs superblock UUID */ __u8 layout_type; __u8 sb_max_size_bits; /* base 2 of 512 byte sectors */ __u8 nr_superblocks; __u8 pad[5]; __le64 sb_offset[61]; } __packed __aligned(8); #define BCH_SB_LAYOUT_SECTOR 7 /* * @offset - sector where this sb was written * @version - on disk format version * @version_min - Oldest metadata version this filesystem contains; so we can * safely drop compatibility code and refuse to mount filesystems * we'd need it for * @magic - identifies as a bcachefs superblock (BCHFS_MAGIC) * @seq - incremented each time superblock is written * @uuid - used for generating various magic numbers and identifying * member devices, never changes * @user_uuid - user visible UUID, may be changed * @label - filesystem label * @seq - identifies most recent superblock, incremented each time * superblock is written * @features - enabled incompatible features */ struct bch_sb { struct bch_csum csum; __le16 version; __le16 version_min; __le16 pad[2]; __uuid_t magic; __uuid_t uuid; __uuid_t user_uuid; __u8 label[BCH_SB_LABEL_SIZE]; __le64 offset; __le64 seq; __le16 block_size; __u8 dev_idx; __u8 nr_devices; __le32 u64s; __le64 time_base_lo; __le32 time_base_hi; __le32 time_precision; __le64 flags[7]; __le64 write_time; __le64 features[2]; __le64 compat[2]; struct bch_sb_layout layout; struct bch_sb_field start[0]; __le64 _data[]; } __packed __aligned(8); /* * Flags: * BCH_SB_INITALIZED - set on first mount * BCH_SB_CLEAN - did we shut down cleanly? Just a hint, doesn't affect * behaviour of mount/recovery path: * BCH_SB_INODE_32BIT - limit inode numbers to 32 bits * BCH_SB_128_BIT_MACS - 128 bit macs instead of 80 * BCH_SB_ENCRYPTION_TYPE - if nonzero encryption is enabled; overrides * DATA/META_CSUM_TYPE. Also indicates encryption * algorithm in use, if/when we get more than one */ LE16_BITMASK(BCH_SB_BLOCK_SIZE, struct bch_sb, block_size, 0, 16); LE64_BITMASK(BCH_SB_INITIALIZED, struct bch_sb, flags[0], 0, 1); LE64_BITMASK(BCH_SB_CLEAN, struct bch_sb, flags[0], 1, 2); LE64_BITMASK(BCH_SB_CSUM_TYPE, struct bch_sb, flags[0], 2, 8); LE64_BITMASK(BCH_SB_ERROR_ACTION, struct bch_sb, flags[0], 8, 12); LE64_BITMASK(BCH_SB_BTREE_NODE_SIZE, struct bch_sb, flags[0], 12, 28); LE64_BITMASK(BCH_SB_GC_RESERVE, struct bch_sb, flags[0], 28, 33); LE64_BITMASK(BCH_SB_ROOT_RESERVE, struct bch_sb, flags[0], 33, 40); LE64_BITMASK(BCH_SB_META_CSUM_TYPE, struct bch_sb, flags[0], 40, 44); LE64_BITMASK(BCH_SB_DATA_CSUM_TYPE, struct bch_sb, flags[0], 44, 48); LE64_BITMASK(BCH_SB_META_REPLICAS_WANT, struct bch_sb, flags[0], 48, 52); LE64_BITMASK(BCH_SB_DATA_REPLICAS_WANT, struct bch_sb, flags[0], 52, 56); LE64_BITMASK(BCH_SB_POSIX_ACL, struct bch_sb, flags[0], 56, 57); LE64_BITMASK(BCH_SB_USRQUOTA, struct bch_sb, flags[0], 57, 58); LE64_BITMASK(BCH_SB_GRPQUOTA, struct bch_sb, flags[0], 58, 59); LE64_BITMASK(BCH_SB_PRJQUOTA, struct bch_sb, flags[0], 59, 60); LE64_BITMASK(BCH_SB_HAS_ERRORS, struct bch_sb, flags[0], 60, 61); LE64_BITMASK(BCH_SB_HAS_TOPOLOGY_ERRORS,struct bch_sb, flags[0], 61, 62); LE64_BITMASK(BCH_SB_BIG_ENDIAN, struct bch_sb, flags[0], 62, 63); LE64_BITMASK(BCH_SB_STR_HASH_TYPE, struct bch_sb, flags[1], 0, 4); LE64_BITMASK(BCH_SB_COMPRESSION_TYPE_LO,struct bch_sb, flags[1], 4, 8); LE64_BITMASK(BCH_SB_INODE_32BIT, struct bch_sb, flags[1], 8, 9); LE64_BITMASK(BCH_SB_128_BIT_MACS, struct bch_sb, flags[1], 9, 10); LE64_BITMASK(BCH_SB_ENCRYPTION_TYPE, struct bch_sb, flags[1], 10, 14); /* * Max size of an extent that may require bouncing to read or write * (checksummed, compressed): 64k */ LE64_BITMASK(BCH_SB_ENCODED_EXTENT_MAX_BITS, struct bch_sb, flags[1], 14, 20); LE64_BITMASK(BCH_SB_META_REPLICAS_REQ, struct bch_sb, flags[1], 20, 24); LE64_BITMASK(BCH_SB_DATA_REPLICAS_REQ, struct bch_sb, flags[1], 24, 28); LE64_BITMASK(BCH_SB_PROMOTE_TARGET, struct bch_sb, flags[1], 28, 40); LE64_BITMASK(BCH_SB_FOREGROUND_TARGET, struct bch_sb, flags[1], 40, 52); LE64_BITMASK(BCH_SB_BACKGROUND_TARGET, struct bch_sb, flags[1], 52, 64); LE64_BITMASK(BCH_SB_BACKGROUND_COMPRESSION_TYPE_LO, struct bch_sb, flags[2], 0, 4); LE64_BITMASK(BCH_SB_GC_RESERVE_BYTES, struct bch_sb, flags[2], 4, 64); LE64_BITMASK(BCH_SB_ERASURE_CODE, struct bch_sb, flags[3], 0, 16); LE64_BITMASK(BCH_SB_METADATA_TARGET, struct bch_sb, flags[3], 16, 28); LE64_BITMASK(BCH_SB_SHARD_INUMS, struct bch_sb, flags[3], 28, 29); LE64_BITMASK(BCH_SB_INODES_USE_KEY_CACHE,struct bch_sb, flags[3], 29, 30); LE64_BITMASK(BCH_SB_JOURNAL_FLUSH_DELAY,struct bch_sb, flags[3], 30, 62); LE64_BITMASK(BCH_SB_JOURNAL_FLUSH_DISABLED,struct bch_sb, flags[3], 62, 63); LE64_BITMASK(BCH_SB_JOURNAL_RECLAIM_DELAY,struct bch_sb, flags[4], 0, 32); LE64_BITMASK(BCH_SB_JOURNAL_TRANSACTION_NAMES,struct bch_sb, flags[4], 32, 33); LE64_BITMASK(BCH_SB_NOCOW, struct bch_sb, flags[4], 33, 34); LE64_BITMASK(BCH_SB_WRITE_BUFFER_SIZE, struct bch_sb, flags[4], 34, 54); LE64_BITMASK(BCH_SB_VERSION_UPGRADE, struct bch_sb, flags[4], 54, 56); LE64_BITMASK(BCH_SB_COMPRESSION_TYPE_HI,struct bch_sb, flags[4], 56, 60); LE64_BITMASK(BCH_SB_BACKGROUND_COMPRESSION_TYPE_HI, struct bch_sb, flags[4], 60, 64); LE64_BITMASK(BCH_SB_VERSION_UPGRADE_COMPLETE, struct bch_sb, flags[5], 0, 16); static inline __u64 BCH_SB_COMPRESSION_TYPE(const struct bch_sb *sb) { return BCH_SB_COMPRESSION_TYPE_LO(sb) | (BCH_SB_COMPRESSION_TYPE_HI(sb) << 4); } static inline void SET_BCH_SB_COMPRESSION_TYPE(struct bch_sb *sb, __u64 v) { SET_BCH_SB_COMPRESSION_TYPE_LO(sb, v); SET_BCH_SB_COMPRESSION_TYPE_HI(sb, v >> 4); } static inline __u64 BCH_SB_BACKGROUND_COMPRESSION_TYPE(const struct bch_sb *sb) { return BCH_SB_BACKGROUND_COMPRESSION_TYPE_LO(sb) | (BCH_SB_BACKGROUND_COMPRESSION_TYPE_HI(sb) << 4); } static inline void SET_BCH_SB_BACKGROUND_COMPRESSION_TYPE(struct bch_sb *sb, __u64 v) { SET_BCH_SB_BACKGROUND_COMPRESSION_TYPE_LO(sb, v); SET_BCH_SB_BACKGROUND_COMPRESSION_TYPE_HI(sb, v >> 4); } /* * Features: * * journal_seq_blacklist_v3: gates BCH_SB_FIELD_journal_seq_blacklist * reflink: gates KEY_TYPE_reflink * inline_data: gates KEY_TYPE_inline_data * new_siphash: gates BCH_STR_HASH_siphash * new_extent_overwrite: gates BTREE_NODE_NEW_EXTENT_OVERWRITE */ #define BCH_SB_FEATURES() \ x(lz4, 0) \ x(gzip, 1) \ x(zstd, 2) \ x(atomic_nlink, 3) \ x(ec, 4) \ x(journal_seq_blacklist_v3, 5) \ x(reflink, 6) \ x(new_siphash, 7) \ x(inline_data, 8) \ x(new_extent_overwrite, 9) \ x(incompressible, 10) \ x(btree_ptr_v2, 11) \ x(extents_above_btree_updates, 12) \ x(btree_updates_journalled, 13) \ x(reflink_inline_data, 14) \ x(new_varint, 15) \ x(journal_no_flush, 16) \ x(alloc_v2, 17) \ x(extents_across_btree_nodes, 18) #define BCH_SB_FEATURES_ALWAYS \ ((1ULL << BCH_FEATURE_new_extent_overwrite)| \ (1ULL << BCH_FEATURE_extents_above_btree_updates)|\ (1ULL << BCH_FEATURE_btree_updates_journalled)|\ (1ULL << BCH_FEATURE_alloc_v2)|\ (1ULL << BCH_FEATURE_extents_across_btree_nodes)) #define BCH_SB_FEATURES_ALL \ (BCH_SB_FEATURES_ALWAYS| \ (1ULL << BCH_FEATURE_new_siphash)| \ (1ULL << BCH_FEATURE_btree_ptr_v2)| \ (1ULL << BCH_FEATURE_new_varint)| \ (1ULL << BCH_FEATURE_journal_no_flush)) enum bch_sb_feature { #define x(f, n) BCH_FEATURE_##f, BCH_SB_FEATURES() #undef x BCH_FEATURE_NR, }; #define BCH_SB_COMPAT() \ x(alloc_info, 0) \ x(alloc_metadata, 1) \ x(extents_above_btree_updates_done, 2) \ x(bformat_overflow_done, 3) enum bch_sb_compat { #define x(f, n) BCH_COMPAT_##f, BCH_SB_COMPAT() #undef x BCH_COMPAT_NR, }; /* options: */ #define BCH_VERSION_UPGRADE_OPTS() \ x(compatible, 0) \ x(incompatible, 1) \ x(none, 2) enum bch_version_upgrade_opts { #define x(t, n) BCH_VERSION_UPGRADE_##t = n, BCH_VERSION_UPGRADE_OPTS() #undef x }; #define BCH_REPLICAS_MAX 4U #define BCH_BKEY_PTRS_MAX 16U #define BCH_ERROR_ACTIONS() \ x(continue, 0) \ x(fix_safe, 1) \ x(panic, 2) \ x(ro, 3) enum bch_error_actions { #define x(t, n) BCH_ON_ERROR_##t = n, BCH_ERROR_ACTIONS() #undef x BCH_ON_ERROR_NR }; #define BCH_STR_HASH_TYPES() \ x(crc32c, 0) \ x(crc64, 1) \ x(siphash_old, 2) \ x(siphash, 3) enum bch_str_hash_type { #define x(t, n) BCH_STR_HASH_##t = n, BCH_STR_HASH_TYPES() #undef x BCH_STR_HASH_NR }; #define BCH_STR_HASH_OPTS() \ x(crc32c, 0) \ x(crc64, 1) \ x(siphash, 2) enum bch_str_hash_opts { #define x(t, n) BCH_STR_HASH_OPT_##t = n, BCH_STR_HASH_OPTS() #undef x BCH_STR_HASH_OPT_NR }; #define BCH_CSUM_TYPES() \ x(none, 0) \ x(crc32c_nonzero, 1) \ x(crc64_nonzero, 2) \ x(chacha20_poly1305_80, 3) \ x(chacha20_poly1305_128, 4) \ x(crc32c, 5) \ x(crc64, 6) \ x(xxhash, 7) enum bch_csum_type { #define x(t, n) BCH_CSUM_##t = n, BCH_CSUM_TYPES() #undef x BCH_CSUM_NR }; static const __maybe_unused unsigned bch_crc_bytes[] = { [BCH_CSUM_none] = 0, [BCH_CSUM_crc32c_nonzero] = 4, [BCH_CSUM_crc32c] = 4, [BCH_CSUM_crc64_nonzero] = 8, [BCH_CSUM_crc64] = 8, [BCH_CSUM_xxhash] = 8, [BCH_CSUM_chacha20_poly1305_80] = 10, [BCH_CSUM_chacha20_poly1305_128] = 16, }; static inline _Bool bch2_csum_type_is_encryption(enum bch_csum_type type) { switch (type) { case BCH_CSUM_chacha20_poly1305_80: case BCH_CSUM_chacha20_poly1305_128: return true; default: return false; } } #define BCH_CSUM_OPTS() \ x(none, 0) \ x(crc32c, 1) \ x(crc64, 2) \ x(xxhash, 3) enum bch_csum_opts { #define x(t, n) BCH_CSUM_OPT_##t = n, BCH_CSUM_OPTS() #undef x BCH_CSUM_OPT_NR }; #define BCH_COMPRESSION_TYPES() \ x(none, 0) \ x(lz4_old, 1) \ x(gzip, 2) \ x(lz4, 3) \ x(zstd, 4) \ x(incompressible, 5) enum bch_compression_type { #define x(t, n) BCH_COMPRESSION_TYPE_##t = n, BCH_COMPRESSION_TYPES() #undef x BCH_COMPRESSION_TYPE_NR }; #define BCH_COMPRESSION_OPTS() \ x(none, 0) \ x(lz4, 1) \ x(gzip, 2) \ x(zstd, 3) enum bch_compression_opts { #define x(t, n) BCH_COMPRESSION_OPT_##t = n, BCH_COMPRESSION_OPTS() #undef x BCH_COMPRESSION_OPT_NR }; /* * Magic numbers * * The various other data structures have their own magic numbers, which are * xored with the first part of the cache set's UUID */ #define BCACHE_MAGIC \ UUID_INIT(0xc68573f6, 0x4e1a, 0x45ca, \ 0x82, 0x65, 0xf5, 0x7f, 0x48, 0xba, 0x6d, 0x81) #define BCHFS_MAGIC \ UUID_INIT(0xc68573f6, 0x66ce, 0x90a9, \ 0xd9, 0x6a, 0x60, 0xcf, 0x80, 0x3d, 0xf7, 0xef) #define BCACHEFS_STATFS_MAGIC BCACHEFS_SUPER_MAGIC #define JSET_MAGIC __cpu_to_le64(0x245235c1a3625032ULL) #define BSET_MAGIC __cpu_to_le64(0x90135c78b99e07f5ULL) static inline __le64 __bch2_sb_magic(struct bch_sb *sb) { __le64 ret; memcpy(&ret, &sb->uuid, sizeof(ret)); return ret; } static inline __u64 __jset_magic(struct bch_sb *sb) { return __le64_to_cpu(__bch2_sb_magic(sb) ^ JSET_MAGIC); } static inline __u64 __bset_magic(struct bch_sb *sb) { return __le64_to_cpu(__bch2_sb_magic(sb) ^ BSET_MAGIC); } /* Journal */ #define JSET_KEYS_U64s (sizeof(struct jset_entry) / sizeof(__u64)) #define BCH_JSET_ENTRY_TYPES() \ x(btree_keys, 0) \ x(btree_root, 1) \ x(prio_ptrs, 2) \ x(blacklist, 3) \ x(blacklist_v2, 4) \ x(usage, 5) \ x(data_usage, 6) \ x(clock, 7) \ x(dev_usage, 8) \ x(log, 9) \ x(overwrite, 10) \ x(write_buffer_keys, 11) \ x(datetime, 12) enum bch_jset_entry_type { #define x(f, nr) BCH_JSET_ENTRY_##f = nr, BCH_JSET_ENTRY_TYPES() #undef x BCH_JSET_ENTRY_NR }; static inline bool jset_entry_is_key(struct jset_entry *e) { switch (e->type) { case BCH_JSET_ENTRY_btree_keys: case BCH_JSET_ENTRY_btree_root: case BCH_JSET_ENTRY_write_buffer_keys: return true; } return false; } /* * Journal sequence numbers can be blacklisted: bsets record the max sequence * number of all the journal entries they contain updates for, so that on * recovery we can ignore those bsets that contain index updates newer that what * made it into the journal. * * This means that we can't reuse that journal_seq - we have to skip it, and * then record that we skipped it so that the next time we crash and recover we * don't think there was a missing journal entry. */ struct jset_entry_blacklist { struct jset_entry entry; __le64 seq; }; struct jset_entry_blacklist_v2 { struct jset_entry entry; __le64 start; __le64 end; }; #define BCH_FS_USAGE_TYPES() \ x(reserved, 0) \ x(inodes, 1) \ x(key_version, 2) enum bch_fs_usage_type { #define x(f, nr) BCH_FS_USAGE_##f = nr, BCH_FS_USAGE_TYPES() #undef x BCH_FS_USAGE_NR }; struct jset_entry_usage { struct jset_entry entry; __le64 v; } __packed; struct jset_entry_data_usage { struct jset_entry entry; __le64 v; struct bch_replicas_entry_v1 r; } __packed; struct jset_entry_clock { struct jset_entry entry; __u8 rw; __u8 pad[7]; __le64 time; } __packed; struct jset_entry_dev_usage_type { __le64 buckets; __le64 sectors; __le64 fragmented; } __packed; struct jset_entry_dev_usage { struct jset_entry entry; __le32 dev; __u32 pad; __le64 _buckets_ec; /* No longer used */ __le64 _buckets_unavailable; /* No longer used */ struct jset_entry_dev_usage_type d[]; }; static inline unsigned jset_entry_dev_usage_nr_types(struct jset_entry_dev_usage *u) { return (vstruct_bytes(&u->entry) - sizeof(struct jset_entry_dev_usage)) / sizeof(struct jset_entry_dev_usage_type); } struct jset_entry_log { struct jset_entry entry; u8 d[]; } __packed __aligned(8); struct jset_entry_datetime { struct jset_entry entry; __le64 seconds; } __packed __aligned(8); /* * On disk format for a journal entry: * seq is monotonically increasing; every journal entry has its own unique * sequence number. * * last_seq is the oldest journal entry that still has keys the btree hasn't * flushed to disk yet. * * version is for on disk format changes. */ struct jset { struct bch_csum csum; __le64 magic; __le64 seq; __le32 version; __le32 flags; __le32 u64s; /* size of d[] in u64s */ __u8 encrypted_start[0]; __le16 _read_clock; /* no longer used */ __le16 _write_clock; /* Sequence number of oldest dirty journal entry */ __le64 last_seq; struct jset_entry start[0]; __u64 _data[]; } __packed __aligned(8); LE32_BITMASK(JSET_CSUM_TYPE, struct jset, flags, 0, 4); LE32_BITMASK(JSET_BIG_ENDIAN, struct jset, flags, 4, 5); LE32_BITMASK(JSET_NO_FLUSH, struct jset, flags, 5, 6); #define BCH_JOURNAL_BUCKETS_MIN 8 /* Btree: */ enum btree_id_flags { BTREE_ID_EXTENTS = BIT(0), BTREE_ID_SNAPSHOTS = BIT(1), BTREE_ID_SNAPSHOT_FIELD = BIT(2), BTREE_ID_DATA = BIT(3), }; #define BCH_BTREE_IDS() \ x(extents, 0, BTREE_ID_EXTENTS|BTREE_ID_SNAPSHOTS|BTREE_ID_DATA,\ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_error)| \ BIT_ULL(KEY_TYPE_cookie)| \ BIT_ULL(KEY_TYPE_extent)| \ BIT_ULL(KEY_TYPE_reservation)| \ BIT_ULL(KEY_TYPE_reflink_p)| \ BIT_ULL(KEY_TYPE_inline_data)) \ x(inodes, 1, BTREE_ID_SNAPSHOTS, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_inode)| \ BIT_ULL(KEY_TYPE_inode_v2)| \ BIT_ULL(KEY_TYPE_inode_v3)| \ BIT_ULL(KEY_TYPE_inode_generation)) \ x(dirents, 2, BTREE_ID_SNAPSHOTS, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_hash_whiteout)| \ BIT_ULL(KEY_TYPE_dirent)) \ x(xattrs, 3, BTREE_ID_SNAPSHOTS, \ BIT_ULL(KEY_TYPE_whiteout)| \ BIT_ULL(KEY_TYPE_cookie)| \ BIT_ULL(KEY_TYPE_hash_whiteout)| \ BIT_ULL(KEY_TYPE_xattr)) \ x(alloc, 4, 0, \ BIT_ULL(KEY_TYPE_alloc)| \ BIT_ULL(KEY_TYPE_alloc_v2)| \ BIT_ULL(KEY_TYPE_alloc_v3)| \ BIT_ULL(KEY_TYPE_alloc_v4)) \ x(quotas, 5, 0, \ BIT_ULL(KEY_TYPE_quota)) \ x(stripes, 6, 0, \ BIT_ULL(KEY_TYPE_stripe)) \ x(reflink, 7, BTREE_ID_EXTENTS|BTREE_ID_DATA, \ BIT_ULL(KEY_TYPE_reflink_v)| \ BIT_ULL(KEY_TYPE_indirect_inline_data)| \ BIT_ULL(KEY_TYPE_error)) \ x(subvolumes, 8, 0, \ BIT_ULL(KEY_TYPE_subvolume)) \ x(snapshots, 9, 0, \ BIT_ULL(KEY_TYPE_snapshot)) \ x(lru, 10, 0, \ BIT_ULL(KEY_TYPE_set)) \ x(freespace, 11, BTREE_ID_EXTENTS, \ BIT_ULL(KEY_TYPE_set)) \ x(need_discard, 12, 0, \ BIT_ULL(KEY_TYPE_set)) \ x(backpointers, 13, 0, \ BIT_ULL(KEY_TYPE_backpointer)) \ x(bucket_gens, 14, 0, \ BIT_ULL(KEY_TYPE_bucket_gens)) \ x(snapshot_trees, 15, 0, \ BIT_ULL(KEY_TYPE_snapshot_tree)) \ x(deleted_inodes, 16, BTREE_ID_SNAPSHOT_FIELD, \ BIT_ULL(KEY_TYPE_set)) \ x(logged_ops, 17, 0, \ BIT_ULL(KEY_TYPE_logged_op_truncate)| \ BIT_ULL(KEY_TYPE_logged_op_finsert)) \ x(rebalance_work, 18, BTREE_ID_SNAPSHOT_FIELD, \ BIT_ULL(KEY_TYPE_set)|BIT_ULL(KEY_TYPE_cookie)) \ x(subvolume_children, 19, 0, \ BIT_ULL(KEY_TYPE_set)) \ x(accounting, 20, BTREE_ID_SNAPSHOT_FIELD, \ BIT_ULL(KEY_TYPE_accounting)) \ enum btree_id { #define x(name, nr, ...) BTREE_ID_##name = nr, BCH_BTREE_IDS() #undef x BTREE_ID_NR }; /* * Maximum number of btrees that we will _ever_ have under the current scheme, * where we refer to them with 64 bit bitfields - and we also need a bit for * the interior btree node type: */ #define BTREE_ID_NR_MAX 63 static inline bool btree_id_is_alloc(enum btree_id id) { switch (id) { case BTREE_ID_alloc: case BTREE_ID_backpointers: case BTREE_ID_need_discard: case BTREE_ID_freespace: case BTREE_ID_bucket_gens: return true; default: return false; } } #define BTREE_MAX_DEPTH 4U /* Btree nodes */ /* * Btree nodes * * On disk a btree node is a list/log of these; within each set the keys are * sorted */ struct bset { __le64 seq; /* * Highest journal entry this bset contains keys for. * If on recovery we don't see that journal entry, this bset is ignored: * this allows us to preserve the order of all index updates after a * crash, since the journal records a total order of all index updates * and anything that didn't make it to the journal doesn't get used. */ __le64 journal_seq; __le32 flags; __le16 version; __le16 u64s; /* count of d[] in u64s */ struct bkey_packed start[0]; __u64 _data[]; } __packed __aligned(8); LE32_BITMASK(BSET_CSUM_TYPE, struct bset, flags, 0, 4); LE32_BITMASK(BSET_BIG_ENDIAN, struct bset, flags, 4, 5); LE32_BITMASK(BSET_SEPARATE_WHITEOUTS, struct bset, flags, 5, 6); /* Sector offset within the btree node: */ LE32_BITMASK(BSET_OFFSET, struct bset, flags, 16, 32); struct btree_node { struct bch_csum csum; __le64 magic; /* this flags field is encrypted, unlike bset->flags: */ __le64 flags; /* Closed interval: */ struct bpos min_key; struct bpos max_key; struct bch_extent_ptr _ptr; /* not used anymore */ struct bkey_format format; union { struct bset keys; struct { __u8 pad[22]; __le16 u64s; __u64 _data[0]; }; }; } __packed __aligned(8); LE64_BITMASK(BTREE_NODE_ID_LO, struct btree_node, flags, 0, 4); LE64_BITMASK(BTREE_NODE_LEVEL, struct btree_node, flags, 4, 8); LE64_BITMASK(BTREE_NODE_NEW_EXTENT_OVERWRITE, struct btree_node, flags, 8, 9); LE64_BITMASK(BTREE_NODE_ID_HI, struct btree_node, flags, 9, 25); /* 25-32 unused */ LE64_BITMASK(BTREE_NODE_SEQ, struct btree_node, flags, 32, 64); static inline __u64 BTREE_NODE_ID(struct btree_node *n) { return BTREE_NODE_ID_LO(n) | (BTREE_NODE_ID_HI(n) << 4); } static inline void SET_BTREE_NODE_ID(struct btree_node *n, __u64 v) { SET_BTREE_NODE_ID_LO(n, v); SET_BTREE_NODE_ID_HI(n, v >> 4); } struct btree_node_entry { struct bch_csum csum; union { struct bset keys; struct { __u8 pad[22]; __le16 u64s; __u64 _data[0]; }; }; } __packed __aligned(8); #endif /* _BCACHEFS_FORMAT_H */ |
| 1 2 39 39 11 11 11 11 11 11 11 11 44 5 39 39 28 11 11 39 5 5 5 5 5 5 2 1 2 9 1 2 1 5 4 1 3 3 38 1 3 32 20 10 2 33 6 39 35 6 39 34 2 31 3 1 19 14 32 32 16 32 1 4 17 4 16 17 2 3 2 1 2 2 7 1 1 5 3 1 1 8 11 11 1 22 23 23 16 5 2 9 1 1 7 7 47 41 6 44 2 42 41 39 21 22 15 1 1 1 2 1 1 1 4 1 1 2 5 24 5 1 1 1 2 1 1 4 1 1 1 1 1 33 35 1 9 10 2 12 1 2 2 16 1 5 10 32 3 1 1 1 1 4 1 5 2 3 4 15 8 1 21 5 1 1 3 2 4 241 241 37 252 42 209 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/ioctl.c * * Copyright (C) 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) */ #include <linux/fs.h> #include <linux/capability.h> #include <linux/time.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/random.h> #include <linux/uaccess.h> #include <linux/delay.h> #include <linux/iversion.h> #include <linux/fileattr.h> #include <linux/uuid.h> #include "ext4_jbd2.h" #include "ext4.h" #include <linux/fsmap.h> #include "fsmap.h" #include <trace/events/ext4.h> typedef void ext4_update_sb_callback(struct ext4_super_block *es, const void *arg); /* * Superblock modification callback function for changing file system * label */ static void ext4_sb_setlabel(struct ext4_super_block *es, const void *arg) { /* Sanity check, this should never happen */ BUILD_BUG_ON(sizeof(es->s_volume_name) < EXT4_LABEL_MAX); memcpy(es->s_volume_name, (char *)arg, EXT4_LABEL_MAX); } /* * Superblock modification callback function for changing file system * UUID. */ static void ext4_sb_setuuid(struct ext4_super_block *es, const void *arg) { memcpy(es->s_uuid, (__u8 *)arg, UUID_SIZE); } static int ext4_update_primary_sb(struct super_block *sb, handle_t *handle, ext4_update_sb_callback func, const void *arg) { int err = 0; struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh = sbi->s_sbh; struct ext4_super_block *es = sbi->s_es; trace_ext4_update_sb(sb, bh->b_blocknr, 1); BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); if (err) goto out_err; lock_buffer(bh); func(es, arg); ext4_superblock_csum_set(sb); unlock_buffer(bh); if (buffer_write_io_error(bh) || !buffer_uptodate(bh)) { ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(bh); set_buffer_uptodate(bh); } err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) goto out_err; err = sync_dirty_buffer(bh); out_err: ext4_std_error(sb, err); return err; } /* * Update one backup superblock in the group 'grp' using the callback * function 'func' and argument 'arg'. If the handle is NULL the * modification is not journalled. * * Returns: 0 when no modification was done (no superblock in the group) * 1 when the modification was successful * <0 on error */ static int ext4_update_backup_sb(struct super_block *sb, handle_t *handle, ext4_group_t grp, ext4_update_sb_callback func, const void *arg) { int err = 0; ext4_fsblk_t sb_block; struct buffer_head *bh; unsigned long offset = 0; struct ext4_super_block *es; if (!ext4_bg_has_super(sb, grp)) return 0; /* * For the group 0 there is always 1k padding, so we have * either adjust offset, or sb_block depending on blocksize */ if (grp == 0) { sb_block = 1 * EXT4_MIN_BLOCK_SIZE; offset = do_div(sb_block, sb->s_blocksize); } else { sb_block = ext4_group_first_block_no(sb, grp); offset = 0; } trace_ext4_update_sb(sb, sb_block, handle ? 1 : 0); bh = ext4_sb_bread(sb, sb_block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); if (handle) { BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); if (err) goto out_bh; } es = (struct ext4_super_block *) (bh->b_data + offset); lock_buffer(bh); if (ext4_has_metadata_csum(sb) && es->s_checksum != ext4_superblock_csum(sb, es)) { ext4_msg(sb, KERN_ERR, "Invalid checksum for backup " "superblock %llu", sb_block); unlock_buffer(bh); goto out_bh; } func(es, arg); if (ext4_has_metadata_csum(sb)) es->s_checksum = ext4_superblock_csum(sb, es); set_buffer_uptodate(bh); unlock_buffer(bh); if (handle) { err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) goto out_bh; } else { BUFFER_TRACE(bh, "marking dirty"); mark_buffer_dirty(bh); } err = sync_dirty_buffer(bh); out_bh: brelse(bh); ext4_std_error(sb, err); return (err) ? err : 1; } /* * Update primary and backup superblocks using the provided function * func and argument arg. * * Only the primary superblock and at most two backup superblock * modifications are journalled; the rest is modified without journal. * This is safe because e2fsck will re-write them if there is a problem, * and we're very unlikely to ever need more than two backups. */ static int ext4_update_superblocks_fn(struct super_block *sb, ext4_update_sb_callback func, const void *arg) { handle_t *handle; ext4_group_t ngroups; unsigned int three = 1; unsigned int five = 5; unsigned int seven = 7; int err = 0, ret, i; ext4_group_t grp, primary_grp; struct ext4_sb_info *sbi = EXT4_SB(sb); /* * We can't update superblocks while the online resize is running */ if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING, &sbi->s_ext4_flags)) { ext4_msg(sb, KERN_ERR, "Can't modify superblock while" "performing online resize"); return -EBUSY; } /* * We're only going to update primary superblock and two * backup superblocks in this transaction. */ handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 3); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto out; } /* Update primary superblock */ err = ext4_update_primary_sb(sb, handle, func, arg); if (err) { ext4_msg(sb, KERN_ERR, "Failed to update primary " "superblock"); goto out_journal; } primary_grp = ext4_get_group_number(sb, sbi->s_sbh->b_blocknr); ngroups = ext4_get_groups_count(sb); /* * Update backup superblocks. We have to start from group 0 * because it might not be where the primary superblock is * if the fs is mounted with -o sb=<backup_sb_block> */ i = 0; grp = 0; while (grp < ngroups) { /* Skip primary superblock */ if (grp == primary_grp) goto next_grp; ret = ext4_update_backup_sb(sb, handle, grp, func, arg); if (ret < 0) { /* Ignore bad checksum; try to update next sb */ if (ret == -EFSBADCRC) goto next_grp; err = ret; goto out_journal; } i += ret; if (handle && i > 1) { /* * We're only journalling primary superblock and * two backup superblocks; the rest is not * journalled. */ err = ext4_journal_stop(handle); if (err) goto out; handle = NULL; } next_grp: grp = ext4_list_backups(sb, &three, &five, &seven); } out_journal: if (handle) { ret = ext4_journal_stop(handle); if (ret && !err) err = ret; } out: clear_bit_unlock(EXT4_FLAGS_RESIZING, &sbi->s_ext4_flags); smp_mb__after_atomic(); return err ? err : 0; } /* * Swap memory between @a and @b for @len bytes. * * @a: pointer to first memory area * @b: pointer to second memory area * @len: number of bytes to swap * */ static void memswap(void *a, void *b, size_t len) { unsigned char *ap, *bp; ap = (unsigned char *)a; bp = (unsigned char *)b; while (len-- > 0) { swap(*ap, *bp); ap++; bp++; } } /* * Swap i_data and associated attributes between @inode1 and @inode2. * This function is used for the primary swap between inode1 and inode2 * and also to revert this primary swap in case of errors. * * Therefore you have to make sure, that calling this method twice * will revert all changes. * * @inode1: pointer to first inode * @inode2: pointer to second inode */ static void swap_inode_data(struct inode *inode1, struct inode *inode2) { loff_t isize; struct ext4_inode_info *ei1; struct ext4_inode_info *ei2; unsigned long tmp; struct timespec64 ts1, ts2; ei1 = EXT4_I(inode1); ei2 = EXT4_I(inode2); swap(inode1->i_version, inode2->i_version); ts1 = inode_get_atime(inode1); ts2 = inode_get_atime(inode2); inode_set_atime_to_ts(inode1, ts2); inode_set_atime_to_ts(inode2, ts1); ts1 = inode_get_mtime(inode1); ts2 = inode_get_mtime(inode2); inode_set_mtime_to_ts(inode1, ts2); inode_set_mtime_to_ts(inode2, ts1); memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data)); tmp = ei1->i_flags & EXT4_FL_SHOULD_SWAP; ei1->i_flags = (ei2->i_flags & EXT4_FL_SHOULD_SWAP) | (ei1->i_flags & ~EXT4_FL_SHOULD_SWAP); ei2->i_flags = tmp | (ei2->i_flags & ~EXT4_FL_SHOULD_SWAP); swap(ei1->i_disksize, ei2->i_disksize); ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS); ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS); isize = i_size_read(inode1); i_size_write(inode1, i_size_read(inode2)); i_size_write(inode2, isize); } void ext4_reset_inode_seed(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); __u32 csum; if (!ext4_has_metadata_csum(inode->i_sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum)); ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen)); } /* * Swap the information from the given @inode and the inode * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other * important fields of the inodes. * * @sb: the super block of the filesystem * @idmap: idmap of the mount the inode was found from * @inode: the inode to swap with EXT4_BOOT_LOADER_INO * */ static long swap_inode_boot_loader(struct super_block *sb, struct mnt_idmap *idmap, struct inode *inode) { handle_t *handle; int err; struct inode *inode_bl; struct ext4_inode_info *ei_bl; qsize_t size, size_bl, diff; blkcnt_t blocks; unsigned short bytes; inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL | EXT4_IGET_BAD); if (IS_ERR(inode_bl)) return PTR_ERR(inode_bl); ei_bl = EXT4_I(inode_bl); /* Protect orig inodes against a truncate and make sure, * that only 1 swap_inode_boot_loader is running. */ lock_two_nondirectories(inode, inode_bl); if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) || IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) || (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) || ext4_has_inline_data(inode)) { err = -EINVAL; goto journal_err_out; } if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || !inode_owner_or_capable(idmap, inode) || !capable(CAP_SYS_ADMIN)) { err = -EPERM; goto journal_err_out; } filemap_invalidate_lock(inode->i_mapping); err = filemap_write_and_wait(inode->i_mapping); if (err) goto err_out; err = filemap_write_and_wait(inode_bl->i_mapping); if (err) goto err_out; /* Wait for all existing dio workers */ inode_dio_wait(inode); inode_dio_wait(inode_bl); truncate_inode_pages(&inode->i_data, 0); truncate_inode_pages(&inode_bl->i_data, 0); handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); if (IS_ERR(handle)) { err = -EINVAL; goto err_out; } ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT, handle); /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(inode, inode_bl); if (is_bad_inode(inode_bl) || !S_ISREG(inode_bl->i_mode)) { /* this inode has never been used as a BOOT_LOADER */ set_nlink(inode_bl, 1); i_uid_write(inode_bl, 0); i_gid_write(inode_bl, 0); inode_bl->i_flags = 0; ei_bl->i_flags = 0; inode_set_iversion(inode_bl, 1); i_size_write(inode_bl, 0); EXT4_I(inode_bl)->i_disksize = inode_bl->i_size; inode_bl->i_mode = S_IFREG; if (ext4_has_feature_extents(sb)) { ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode_bl); } else memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data)); } err = dquot_initialize(inode); if (err) goto err_out1; size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes; size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes; diff = size - size_bl; swap_inode_data(inode, inode_bl); inode_set_ctime_current(inode); inode_set_ctime_current(inode_bl); inode_inc_iversion(inode); inode->i_generation = get_random_u32(); inode_bl->i_generation = get_random_u32(); ext4_reset_inode_seed(inode); ext4_reset_inode_seed(inode_bl); ext4_discard_preallocations(inode); err = ext4_mark_inode_dirty(handle, inode); if (err < 0) { /* No need to update quota information. */ ext4_warning(inode->i_sb, "couldn't mark inode #%lu dirty (err %d)", inode->i_ino, err); /* Revert all changes: */ swap_inode_data(inode, inode_bl); ext4_mark_inode_dirty(handle, inode); goto err_out1; } blocks = inode_bl->i_blocks; bytes = inode_bl->i_bytes; inode_bl->i_blocks = inode->i_blocks; inode_bl->i_bytes = inode->i_bytes; err = ext4_mark_inode_dirty(handle, inode_bl); if (err < 0) { /* No need to update quota information. */ ext4_warning(inode_bl->i_sb, "couldn't mark inode #%lu dirty (err %d)", inode_bl->i_ino, err); goto revert; } /* Bootloader inode should not be counted into quota information. */ if (diff > 0) dquot_free_space(inode, diff); else err = dquot_alloc_space(inode, -1 * diff); if (err < 0) { revert: /* Revert all changes: */ inode_bl->i_blocks = blocks; inode_bl->i_bytes = bytes; swap_inode_data(inode, inode_bl); ext4_mark_inode_dirty(handle, inode); ext4_mark_inode_dirty(handle, inode_bl); } err_out1: ext4_journal_stop(handle); ext4_double_up_write_data_sem(inode, inode_bl); err_out: filemap_invalidate_unlock(inode->i_mapping); journal_err_out: unlock_two_nondirectories(inode, inode_bl); iput(inode_bl); return err; } /* * If immutable is set and we are not clearing it, we're not allowed to change * anything else in the inode. Don't error out if we're only trying to set * immutable on an immutable file. */ static int ext4_ioctl_check_immutable(struct inode *inode, __u32 new_projid, unsigned int flags) { struct ext4_inode_info *ei = EXT4_I(inode); unsigned int oldflags = ei->i_flags; if (!(oldflags & EXT4_IMMUTABLE_FL) || !(flags & EXT4_IMMUTABLE_FL)) return 0; if ((oldflags & ~EXT4_IMMUTABLE_FL) != (flags & ~EXT4_IMMUTABLE_FL)) return -EPERM; if (ext4_has_feature_project(inode->i_sb) && __kprojid_val(ei->i_projid) != new_projid) return -EPERM; return 0; } static void ext4_dax_dontcache(struct inode *inode, unsigned int flags) { struct ext4_inode_info *ei = EXT4_I(inode); if (S_ISDIR(inode->i_mode)) return; if (test_opt2(inode->i_sb, DAX_NEVER) || test_opt(inode->i_sb, DAX_ALWAYS)) return; if ((ei->i_flags ^ flags) & EXT4_DAX_FL) d_mark_dontcache(inode); } static bool dax_compatible(struct inode *inode, unsigned int oldflags, unsigned int flags) { /* Allow the DAX flag to be changed on inline directories */ if (S_ISDIR(inode->i_mode)) { flags &= ~EXT4_INLINE_DATA_FL; oldflags &= ~EXT4_INLINE_DATA_FL; } if (flags & EXT4_DAX_FL) { if ((oldflags & EXT4_DAX_MUT_EXCL) || ext4_test_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS)) { return false; } } if ((flags & EXT4_DAX_MUT_EXCL) && (oldflags & EXT4_DAX_FL)) return false; return true; } static int ext4_ioctl_setflags(struct inode *inode, unsigned int flags) { struct ext4_inode_info *ei = EXT4_I(inode); handle_t *handle = NULL; int err = -EPERM, migrate = 0; struct ext4_iloc iloc; unsigned int oldflags, mask, i; struct super_block *sb = inode->i_sb; /* Is it quota file? Do not allow user to mess with it */ if (ext4_is_quota_file(inode)) goto flags_out; oldflags = ei->i_flags; /* * The JOURNAL_DATA flag can only be changed by * the relevant capability. */ if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { if (!capable(CAP_SYS_RESOURCE)) goto flags_out; } if (!dax_compatible(inode, oldflags, flags)) { err = -EOPNOTSUPP; goto flags_out; } if ((flags ^ oldflags) & EXT4_EXTENTS_FL) migrate = 1; if ((flags ^ oldflags) & EXT4_CASEFOLD_FL) { if (!ext4_has_feature_casefold(sb)) { err = -EOPNOTSUPP; goto flags_out; } if (!S_ISDIR(inode->i_mode)) { err = -ENOTDIR; goto flags_out; } if (!ext4_empty_dir(inode)) { err = -ENOTEMPTY; goto flags_out; } } /* * Wait for all pending directio and then flush all the dirty pages * for this file. The flush marks all the pages readonly, so any * subsequent attempt to write to the file (particularly mmap pages) * will come through the filesystem and fail. */ if (S_ISREG(inode->i_mode) && !IS_IMMUTABLE(inode) && (flags & EXT4_IMMUTABLE_FL)) { inode_dio_wait(inode); err = filemap_write_and_wait(inode->i_mapping); if (err) goto flags_out; } handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto flags_out; } if (IS_SYNC(inode)) ext4_handle_sync(handle); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto flags_err; ext4_dax_dontcache(inode, flags); for (i = 0, mask = 1; i < 32; i++, mask <<= 1) { if (!(mask & EXT4_FL_USER_MODIFIABLE)) continue; /* These flags get special treatment later */ if (mask == EXT4_JOURNAL_DATA_FL || mask == EXT4_EXTENTS_FL) continue; if (mask & flags) ext4_set_inode_flag(inode, i); else ext4_clear_inode_flag(inode, i); } ext4_set_inode_flags(inode, false); inode_set_ctime_current(inode); inode_inc_iversion(inode); err = ext4_mark_iloc_dirty(handle, inode, &iloc); flags_err: ext4_journal_stop(handle); if (err) goto flags_out; if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { /* * Changes to the journaling mode can cause unsafe changes to * S_DAX if the inode is DAX */ if (IS_DAX(inode)) { err = -EBUSY; goto flags_out; } err = ext4_change_inode_journal_flag(inode, flags & EXT4_JOURNAL_DATA_FL); if (err) goto flags_out; } if (migrate) { if (flags & EXT4_EXTENTS_FL) err = ext4_ext_migrate(inode); else err = ext4_ind_migrate(inode); } flags_out: return err; } #ifdef CONFIG_QUOTA static int ext4_ioctl_setproject(struct inode *inode, __u32 projid) { struct super_block *sb = inode->i_sb; struct ext4_inode_info *ei = EXT4_I(inode); int err, rc; handle_t *handle; kprojid_t kprojid; struct ext4_iloc iloc; struct ext4_inode *raw_inode; struct dquot *transfer_to[MAXQUOTAS] = { }; if (!ext4_has_feature_project(sb)) { if (projid != EXT4_DEF_PROJID) return -EOPNOTSUPP; else return 0; } if (EXT4_INODE_SIZE(sb) <= EXT4_GOOD_OLD_INODE_SIZE) return -EOPNOTSUPP; kprojid = make_kprojid(&init_user_ns, (projid_t)projid); if (projid_eq(kprojid, EXT4_I(inode)->i_projid)) return 0; err = -EPERM; /* Is it quota file? Do not allow user to mess with it */ if (ext4_is_quota_file(inode)) return err; err = dquot_initialize(inode); if (err) return err; err = ext4_get_inode_loc(inode, &iloc); if (err) return err; raw_inode = ext4_raw_inode(&iloc); if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) { err = ext4_expand_extra_isize(inode, EXT4_SB(sb)->s_want_extra_isize, &iloc); if (err) return err; } else { brelse(iloc.bh); } handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(sb) + EXT4_QUOTA_DEL_BLOCKS(sb) + 3); if (IS_ERR(handle)) return PTR_ERR(handle); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto out_stop; transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); if (!IS_ERR(transfer_to[PRJQUOTA])) { /* __dquot_transfer() calls back ext4_get_inode_usage() which * counts xattr inode references. */ down_read(&EXT4_I(inode)->xattr_sem); err = __dquot_transfer(inode, transfer_to); up_read(&EXT4_I(inode)->xattr_sem); dqput(transfer_to[PRJQUOTA]); if (err) goto out_dirty; } EXT4_I(inode)->i_projid = kprojid; inode_set_ctime_current(inode); inode_inc_iversion(inode); out_dirty: rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; out_stop: ext4_journal_stop(handle); return err; } #else static int ext4_ioctl_setproject(struct inode *inode, __u32 projid) { if (projid != EXT4_DEF_PROJID) return -EOPNOTSUPP; return 0; } #endif int ext4_force_shutdown(struct super_block *sb, u32 flags) { struct ext4_sb_info *sbi = EXT4_SB(sb); int ret; if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH) return -EINVAL; if (ext4_forced_shutdown(sb)) return 0; ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags); trace_ext4_shutdown(sb, flags); switch (flags) { case EXT4_GOING_FLAGS_DEFAULT: ret = bdev_freeze(sb->s_bdev); if (ret) return ret; set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); bdev_thaw(sb->s_bdev); break; case EXT4_GOING_FLAGS_LOGFLUSH: set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) { (void) ext4_force_commit(sb); jbd2_journal_abort(sbi->s_journal, -ESHUTDOWN); } break; case EXT4_GOING_FLAGS_NOLOGFLUSH: set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) jbd2_journal_abort(sbi->s_journal, -ESHUTDOWN); break; default: return -EINVAL; } clear_opt(sb, DISCARD); return 0; } static int ext4_ioctl_shutdown(struct super_block *sb, unsigned long arg) { u32 flags; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(flags, (__u32 __user *)arg)) return -EFAULT; return ext4_force_shutdown(sb, flags); } struct getfsmap_info { struct super_block *gi_sb; struct fsmap_head __user *gi_data; unsigned int gi_idx; __u32 gi_last_flags; }; static int ext4_getfsmap_format(struct ext4_fsmap *xfm, void *priv) { struct getfsmap_info *info = priv; struct fsmap fm; trace_ext4_getfsmap_mapping(info->gi_sb, xfm); info->gi_last_flags = xfm->fmr_flags; ext4_fsmap_from_internal(info->gi_sb, &fm, xfm); if (copy_to_user(&info->gi_data->fmh_recs[info->gi_idx++], &fm, sizeof(struct fsmap))) return -EFAULT; return 0; } static int ext4_ioc_getfsmap(struct super_block *sb, struct fsmap_head __user *arg) { struct getfsmap_info info = { NULL }; struct ext4_fsmap_head xhead = {0}; struct fsmap_head head; bool aborted = false; int error; if (copy_from_user(&head, arg, sizeof(struct fsmap_head))) return -EFAULT; if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) || memchr_inv(head.fmh_keys[0].fmr_reserved, 0, sizeof(head.fmh_keys[0].fmr_reserved)) || memchr_inv(head.fmh_keys[1].fmr_reserved, 0, sizeof(head.fmh_keys[1].fmr_reserved))) return -EINVAL; /* * ext4 doesn't report file extents at all, so the only valid * file offsets are the magic ones (all zeroes or all ones). */ if (head.fmh_keys[0].fmr_offset || (head.fmh_keys[1].fmr_offset != 0 && head.fmh_keys[1].fmr_offset != -1ULL)) return -EINVAL; xhead.fmh_iflags = head.fmh_iflags; xhead.fmh_count = head.fmh_count; ext4_fsmap_to_internal(sb, &xhead.fmh_keys[0], &head.fmh_keys[0]); ext4_fsmap_to_internal(sb, &xhead.fmh_keys[1], &head.fmh_keys[1]); trace_ext4_getfsmap_low_key(sb, &xhead.fmh_keys[0]); trace_ext4_getfsmap_high_key(sb, &xhead.fmh_keys[1]); info.gi_sb = sb; info.gi_data = arg; error = ext4_getfsmap(sb, &xhead, ext4_getfsmap_format, &info); if (error == EXT4_QUERY_RANGE_ABORT) aborted = true; else if (error) return error; /* If we didn't abort, set the "last" flag in the last fmx */ if (!aborted && info.gi_idx) { info.gi_last_flags |= FMR_OF_LAST; if (copy_to_user(&info.gi_data->fmh_recs[info.gi_idx - 1].fmr_flags, &info.gi_last_flags, sizeof(info.gi_last_flags))) return -EFAULT; } /* copy back header */ head.fmh_entries = xhead.fmh_entries; head.fmh_oflags = xhead.fmh_oflags; if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) return -EFAULT; return 0; } static long ext4_ioctl_group_add(struct file *file, struct ext4_new_group_data *input) { struct super_block *sb = file_inode(file)->i_sb; int err, err2=0; err = ext4_resize_begin(sb); if (err) return err; if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); err = -EOPNOTSUPP; goto group_add_out; } err = mnt_want_write_file(file); if (err) goto group_add_out; err = ext4_group_add(sb, input); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(file); if (!err && ext4_has_group_desc_csum(sb) && test_opt(sb, INIT_INODE_TABLE)) err = ext4_register_li_request(sb, input->group); group_add_out: err2 = ext4_resize_end(sb, false); if (err == 0) err = err2; return err; } int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct ext4_inode_info *ei = EXT4_I(inode); u32 flags = ei->i_flags & EXT4_FL_USER_VISIBLE; if (S_ISREG(inode->i_mode)) flags &= ~FS_PROJINHERIT_FL; fileattr_fill_flags(fa, flags); if (ext4_has_feature_project(inode->i_sb)) fa->fsx_projid = from_kprojid(&init_user_ns, ei->i_projid); return 0; } int ext4_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); u32 flags = fa->flags; int err = -EOPNOTSUPP; if (flags & ~EXT4_FL_USER_VISIBLE) goto out; /* * chattr(1) grabs flags via GETFLAGS, modifies the result and * passes that to SETFLAGS. So we cannot easily make SETFLAGS * more restrictive than just silently masking off visible but * not settable flags as we always did. */ flags &= EXT4_FL_USER_MODIFIABLE; if (ext4_mask_flags(inode->i_mode, flags) != flags) goto out; err = ext4_ioctl_check_immutable(inode, fa->fsx_projid, flags); if (err) goto out; err = ext4_ioctl_setflags(inode, flags); if (err) goto out; err = ext4_ioctl_setproject(inode, fa->fsx_projid); out: return err; } /* So that the fiemap access checks can't overflow on 32 bit machines. */ #define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg) { struct fiemap fiemap; struct fiemap __user *ufiemap = (struct fiemap __user *) arg; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); int error; if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) return -EFAULT; if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; error = ext4_get_es_cache(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) error = -EFAULT; return error; } static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) { int err = 0; __u32 flags = 0; unsigned int flush_flags = 0; struct super_block *sb = file_inode(filp)->i_sb; if (copy_from_user(&flags, (__u32 __user *)arg, sizeof(__u32))) return -EFAULT; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* check for invalid bits set */ if ((flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID) || ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && (flags & JBD2_JOURNAL_FLUSH_ZEROOUT))) return -EINVAL; if (!EXT4_SB(sb)->s_journal) return -ENODEV; if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !bdev_max_discard_sectors(EXT4_SB(sb)->s_journal->j_dev)) return -EOPNOTSUPP; if (flags & EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN) return 0; if (flags & EXT4_IOC_CHECKPOINT_FLAG_DISCARD) flush_flags |= JBD2_JOURNAL_FLUSH_DISCARD; if (flags & EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT) { flush_flags |= JBD2_JOURNAL_FLUSH_ZEROOUT; pr_info_ratelimited("warning: checkpointing journal with EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT can be slow"); } jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, flush_flags); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); return err; } static int ext4_ioctl_setlabel(struct file *filp, const char __user *user_label) { size_t len; int ret = 0; char new_label[EXT4_LABEL_MAX + 1]; struct super_block *sb = file_inode(filp)->i_sb; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * Copy the maximum length allowed for ext4 label with one more to * find the required terminating null byte in order to test the * label length. The on disk label doesn't need to be null terminated. */ if (copy_from_user(new_label, user_label, EXT4_LABEL_MAX + 1)) return -EFAULT; len = strnlen(new_label, EXT4_LABEL_MAX + 1); if (len > EXT4_LABEL_MAX) return -EINVAL; /* * Clear the buffer after the new label */ memset(new_label + len, 0, EXT4_LABEL_MAX - len); ret = mnt_want_write_file(filp); if (ret) return ret; ret = ext4_update_superblocks_fn(sb, ext4_sb_setlabel, new_label); mnt_drop_write_file(filp); return ret; } static int ext4_ioctl_getlabel(struct ext4_sb_info *sbi, char __user *user_label) { char label[EXT4_LABEL_MAX + 1]; /* * EXT4_LABEL_MAX must always be smaller than FSLABEL_MAX because * FSLABEL_MAX must include terminating null byte, while s_volume_name * does not have to. */ BUILD_BUG_ON(EXT4_LABEL_MAX >= FSLABEL_MAX); lock_buffer(sbi->s_sbh); memtostr_pad(label, sbi->s_es->s_volume_name); unlock_buffer(sbi->s_sbh); if (copy_to_user(user_label, label, sizeof(label))) return -EFAULT; return 0; } static int ext4_ioctl_getuuid(struct ext4_sb_info *sbi, struct fsuuid __user *ufsuuid) { struct fsuuid fsuuid; __u8 uuid[UUID_SIZE]; if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid))) return -EFAULT; if (fsuuid.fsu_len == 0) { fsuuid.fsu_len = UUID_SIZE; if (copy_to_user(&ufsuuid->fsu_len, &fsuuid.fsu_len, sizeof(fsuuid.fsu_len))) return -EFAULT; return 0; } if (fsuuid.fsu_len < UUID_SIZE || fsuuid.fsu_flags != 0) return -EINVAL; lock_buffer(sbi->s_sbh); memcpy(uuid, sbi->s_es->s_uuid, UUID_SIZE); unlock_buffer(sbi->s_sbh); fsuuid.fsu_len = UUID_SIZE; if (copy_to_user(ufsuuid, &fsuuid, sizeof(fsuuid)) || copy_to_user(&ufsuuid->fsu_uuid[0], uuid, UUID_SIZE)) return -EFAULT; return 0; } static int ext4_ioctl_setuuid(struct file *filp, const struct fsuuid __user *ufsuuid) { int ret = 0; struct super_block *sb = file_inode(filp)->i_sb; struct fsuuid fsuuid; __u8 uuid[UUID_SIZE]; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * If any checksums (group descriptors or metadata) are being used * then the checksum seed feature is required to change the UUID. */ if (((ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb)) && !ext4_has_feature_csum_seed(sb)) || ext4_has_feature_stable_inodes(sb)) return -EOPNOTSUPP; if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid))) return -EFAULT; if (fsuuid.fsu_len != UUID_SIZE || fsuuid.fsu_flags != 0) return -EINVAL; if (copy_from_user(uuid, &ufsuuid->fsu_uuid[0], UUID_SIZE)) return -EFAULT; ret = mnt_want_write_file(filp); if (ret) return ret; ret = ext4_update_superblocks_fn(sb, ext4_sb_setuuid, &uuid); mnt_drop_write_file(filp); return ret; } static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; struct mnt_idmap *idmap = file_mnt_idmap(filp); ext4_debug("cmd = %u, arg = %lu\n", cmd, arg); switch (cmd) { case FS_IOC_GETFSMAP: return ext4_ioc_getfsmap(sb, (void __user *)arg); case EXT4_IOC_GETVERSION: case EXT4_IOC_GETVERSION_OLD: return put_user(inode->i_generation, (int __user *) arg); case EXT4_IOC_SETVERSION: case EXT4_IOC_SETVERSION_OLD: { handle_t *handle; struct ext4_iloc iloc; __u32 generation; int err; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (ext4_has_metadata_csum(inode->i_sb)) { ext4_warning(sb, "Setting inode version is not " "supported with metadata_csum enabled."); return -ENOTTY; } err = mnt_want_write_file(filp); if (err) return err; if (get_user(generation, (int __user *) arg)) { err = -EFAULT; goto setversion_out; } inode_lock(inode); handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto unlock_out; } err = ext4_reserve_inode_write(handle, inode, &iloc); if (err == 0) { inode_set_ctime_current(inode); inode_inc_iversion(inode); inode->i_generation = generation; err = ext4_mark_iloc_dirty(handle, inode, &iloc); } ext4_journal_stop(handle); unlock_out: inode_unlock(inode); setversion_out: mnt_drop_write_file(filp); return err; } case EXT4_IOC_GROUP_EXTEND: { ext4_fsblk_t n_blocks_count; int err, err2=0; err = ext4_resize_begin(sb); if (err) return err; if (get_user(n_blocks_count, (__u32 __user *)arg)) { err = -EFAULT; goto group_extend_out; } if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); err = -EOPNOTSUPP; goto group_extend_out; } err = mnt_want_write_file(filp); if (err) goto group_extend_out; err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(filp); group_extend_out: err2 = ext4_resize_end(sb, false); if (err == 0) err = err2; return err; } case EXT4_IOC_MOVE_EXT: { struct move_extent me; struct fd donor; int err; if (!(filp->f_mode & FMODE_READ) || !(filp->f_mode & FMODE_WRITE)) return -EBADF; if (copy_from_user(&me, (struct move_extent __user *)arg, sizeof(me))) return -EFAULT; me.moved_len = 0; donor = fdget(me.donor_fd); if (!donor.file) return -EBADF; if (!(donor.file->f_mode & FMODE_WRITE)) { err = -EBADF; goto mext_out; } if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online defrag not supported with bigalloc"); err = -EOPNOTSUPP; goto mext_out; } else if (IS_DAX(inode)) { ext4_msg(sb, KERN_ERR, "Online defrag not supported with DAX"); err = -EOPNOTSUPP; goto mext_out; } err = mnt_want_write_file(filp); if (err) goto mext_out; err = ext4_move_extents(filp, donor.file, me.orig_start, me.donor_start, me.len, &me.moved_len); mnt_drop_write_file(filp); if (copy_to_user((struct move_extent __user *)arg, &me, sizeof(me))) err = -EFAULT; mext_out: fdput(donor); return err; } case EXT4_IOC_GROUP_ADD: { struct ext4_new_group_data input; if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg, sizeof(input))) return -EFAULT; return ext4_ioctl_group_add(filp, &input); } case EXT4_IOC_MIGRATE: { int err; if (!inode_owner_or_capable(idmap, inode)) return -EACCES; err = mnt_want_write_file(filp); if (err) return err; /* * inode_mutex prevent write and truncate on the file. * Read still goes through. We take i_data_sem in * ext4_ext_swap_inode_data before we switch the * inode format to prevent read. */ inode_lock((inode)); err = ext4_ext_migrate(inode); inode_unlock((inode)); mnt_drop_write_file(filp); return err; } case EXT4_IOC_ALLOC_DA_BLKS: { int err; if (!inode_owner_or_capable(idmap, inode)) return -EACCES; err = mnt_want_write_file(filp); if (err) return err; err = ext4_alloc_da_blocks(inode); mnt_drop_write_file(filp); return err; } case EXT4_IOC_SWAP_BOOT: { int err; if (!(filp->f_mode & FMODE_WRITE)) return -EBADF; err = mnt_want_write_file(filp); if (err) return err; err = swap_inode_boot_loader(sb, idmap, inode); mnt_drop_write_file(filp); return err; } case EXT4_IOC_RESIZE_FS: { ext4_fsblk_t n_blocks_count; int err = 0, err2 = 0; ext4_group_t o_group = EXT4_SB(sb)->s_groups_count; if (copy_from_user(&n_blocks_count, (__u64 __user *)arg, sizeof(__u64))) { return -EFAULT; } err = ext4_resize_begin(sb); if (err) return err; err = mnt_want_write_file(filp); if (err) goto resizefs_out; err = ext4_resize_fs(sb, n_blocks_count); if (EXT4_SB(sb)->s_journal) { ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE, NULL); jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(filp); if (!err && (o_group < EXT4_SB(sb)->s_groups_count) && ext4_has_group_desc_csum(sb) && test_opt(sb, INIT_INODE_TABLE)) err = ext4_register_li_request(sb, o_group); resizefs_out: err2 = ext4_resize_end(sb, true); if (err == 0) err = err2; return err; } case FITRIM: { struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; /* * We haven't replayed the journal, so we cannot use our * block-bitmap-guided storage zapping commands. */ if (test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) return -EROFS; if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; ret = ext4_trim_fs(sb, &range); if (ret < 0) return ret; if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range))) return -EFAULT; return 0; } case EXT4_IOC_PRECACHE_EXTENTS: return ext4_ext_precache(inode); case FS_IOC_SET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); case FS_IOC_GET_ENCRYPTION_PWSALT: return ext4_ioctl_get_encryption_pwsalt(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_policy(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_POLICY_EX: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_policy_ex(filp, (void __user *)arg); case FS_IOC_ADD_ENCRYPTION_KEY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_add_key(filp, (void __user *)arg); case FS_IOC_REMOVE_ENCRYPTION_KEY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_remove_key(filp, (void __user *)arg); case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_remove_key_all_users(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_KEY_STATUS: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_key_status(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_NONCE: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_nonce(filp, (void __user *)arg); case EXT4_IOC_CLEAR_ES_CACHE: { if (!inode_owner_or_capable(idmap, inode)) return -EACCES; ext4_clear_inode_es(inode); return 0; } case EXT4_IOC_GETSTATE: { __u32 state = 0; if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED)) state |= EXT4_STATE_FLAG_EXT_PRECACHED; if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) state |= EXT4_STATE_FLAG_NEW; if (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) state |= EXT4_STATE_FLAG_NEWENTRY; if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) state |= EXT4_STATE_FLAG_DA_ALLOC_CLOSE; return put_user(state, (__u32 __user *) arg); } case EXT4_IOC_GET_ES_CACHE: return ext4_ioctl_get_es_cache(filp, arg); case EXT4_IOC_SHUTDOWN: return ext4_ioctl_shutdown(sb, arg); case FS_IOC_ENABLE_VERITY: if (!ext4_has_feature_verity(sb)) return -EOPNOTSUPP; return fsverity_ioctl_enable(filp, (const void __user *)arg); case FS_IOC_MEASURE_VERITY: if (!ext4_has_feature_verity(sb)) return -EOPNOTSUPP; return fsverity_ioctl_measure(filp, (void __user *)arg); case FS_IOC_READ_VERITY_METADATA: if (!ext4_has_feature_verity(sb)) return -EOPNOTSUPP; return fsverity_ioctl_read_metadata(filp, (const void __user *)arg); case EXT4_IOC_CHECKPOINT: return ext4_ioctl_checkpoint(filp, arg); case FS_IOC_GETFSLABEL: return ext4_ioctl_getlabel(EXT4_SB(sb), (void __user *)arg); case FS_IOC_SETFSLABEL: return ext4_ioctl_setlabel(filp, (const void __user *)arg); case EXT4_IOC_GETFSUUID: return ext4_ioctl_getuuid(EXT4_SB(sb), (void __user *)arg); case EXT4_IOC_SETFSUUID: return ext4_ioctl_setuuid(filp, (const void __user *)arg); default: return -ENOTTY; } } long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { return __ext4_ioctl(filp, cmd, arg); } #ifdef CONFIG_COMPAT long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { /* These are just misnamed, they actually get/put from/to user an int */ switch (cmd) { case EXT4_IOC32_GETVERSION: cmd = EXT4_IOC_GETVERSION; break; case EXT4_IOC32_SETVERSION: cmd = EXT4_IOC_SETVERSION; break; case EXT4_IOC32_GROUP_EXTEND: cmd = EXT4_IOC_GROUP_EXTEND; break; case EXT4_IOC32_GETVERSION_OLD: cmd = EXT4_IOC_GETVERSION_OLD; break; case EXT4_IOC32_SETVERSION_OLD: cmd = EXT4_IOC_SETVERSION_OLD; break; case EXT4_IOC32_GETRSVSZ: cmd = EXT4_IOC_GETRSVSZ; break; case EXT4_IOC32_SETRSVSZ: cmd = EXT4_IOC_SETRSVSZ; break; case EXT4_IOC32_GROUP_ADD: { struct compat_ext4_new_group_input __user *uinput; struct ext4_new_group_data input; int err; uinput = compat_ptr(arg); err = get_user(input.group, &uinput->group); err |= get_user(input.block_bitmap, &uinput->block_bitmap); err |= get_user(input.inode_bitmap, &uinput->inode_bitmap); err |= get_user(input.inode_table, &uinput->inode_table); err |= get_user(input.blocks_count, &uinput->blocks_count); err |= get_user(input.reserved_blocks, &uinput->reserved_blocks); if (err) return -EFAULT; return ext4_ioctl_group_add(file, &input); } case EXT4_IOC_MOVE_EXT: case EXT4_IOC_RESIZE_FS: case FITRIM: case EXT4_IOC_PRECACHE_EXTENTS: case FS_IOC_SET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_PWSALT: case FS_IOC_GET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_POLICY_EX: case FS_IOC_ADD_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: case FS_IOC_GET_ENCRYPTION_KEY_STATUS: case FS_IOC_GET_ENCRYPTION_NONCE: case EXT4_IOC_SHUTDOWN: case FS_IOC_GETFSMAP: case FS_IOC_ENABLE_VERITY: case FS_IOC_MEASURE_VERITY: case FS_IOC_READ_VERITY_METADATA: case EXT4_IOC_CLEAR_ES_CACHE: case EXT4_IOC_GETSTATE: case EXT4_IOC_GET_ES_CACHE: case EXT4_IOC_CHECKPOINT: case FS_IOC_GETFSLABEL: case FS_IOC_SETFSLABEL: case EXT4_IOC_GETFSUUID: case EXT4_IOC_SETFSUUID: break; default: return -ENOIOCTLCMD; } return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif static void set_overhead(struct ext4_super_block *es, const void *arg) { es->s_overhead_clusters = cpu_to_le32(*((unsigned long *) arg)); } int ext4_update_overhead(struct super_block *sb, bool force) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (sb_rdonly(sb)) return 0; if (!force && (sbi->s_overhead == 0 || sbi->s_overhead == le32_to_cpu(sbi->s_es->s_overhead_clusters))) return 0; return ext4_update_superblocks_fn(sb, set_overhead, &sbi->s_overhead); } |
| 2894 2895 2889 2885 2891 2891 2889 2858 2890 1755 2890 2891 101 43 2892 1707 1710 1711 1707 1 2884 2889 1711 1708 193 193 2885 2859 193 1 2885 2887 2889 6 2887 2889 2884 1 2884 2889 6 101 101 101 16 95 95 95 2885 2883 2888 2887 6 6 2876 2876 2878 2879 6 6 2875 10 101 101 101 101 10 101 101 101 101 101 100 2880 2877 2882 2884 36 2886 2889 2886 2889 2888 2889 2861 193 2888 2885 2884 2885 2885 2889 131 130 2878 2879 2891 2884 2891 2893 2875 2880 2875 2877 2893 2894 2893 2895 2888 2885 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/irqflags.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/bug.h> #include "printk_ringbuffer.h" #include "internal.h" /** * DOC: printk_ringbuffer overview * * Data Structure * -------------- * The printk_ringbuffer is made up of 3 internal ringbuffers: * * desc_ring * A ring of descriptors and their meta data (such as sequence number, * timestamp, loglevel, etc.) as well as internal state information about * the record and logical positions specifying where in the other * ringbuffer the text strings are located. * * text_data_ring * A ring of data blocks. A data block consists of an unsigned long * integer (ID) that maps to a desc_ring index followed by the text * string of the record. * * The internal state information of a descriptor is the key element to allow * readers and writers to locklessly synchronize access to the data. * * Implementation * -------------- * * Descriptor Ring * ~~~~~~~~~~~~~~~ * The descriptor ring is an array of descriptors. A descriptor contains * essential meta data to track the data of a printk record using * blk_lpos structs pointing to associated text data blocks (see * "Data Rings" below). Each descriptor is assigned an ID that maps * directly to index values of the descriptor array and has a state. The ID * and the state are bitwise combined into a single descriptor field named * @state_var, allowing ID and state to be synchronously and atomically * updated. * * Descriptors have four states: * * reserved * A writer is modifying the record. * * committed * The record and all its data are written. A writer can reopen the * descriptor (transitioning it back to reserved), but in the committed * state the data is consistent. * * finalized * The record and all its data are complete and available for reading. A * writer cannot reopen the descriptor. * * reusable * The record exists, but its text and/or meta data may no longer be * available. * * Querying the @state_var of a record requires providing the ID of the * descriptor to query. This can yield a possible fifth (pseudo) state: * * miss * The descriptor being queried has an unexpected ID. * * The descriptor ring has a @tail_id that contains the ID of the oldest * descriptor and @head_id that contains the ID of the newest descriptor. * * When a new descriptor should be created (and the ring is full), the tail * descriptor is invalidated by first transitioning to the reusable state and * then invalidating all tail data blocks up to and including the data blocks * associated with the tail descriptor (for the text ring). Then * @tail_id is advanced, followed by advancing @head_id. And finally the * @state_var of the new descriptor is initialized to the new ID and reserved * state. * * The @tail_id can only be advanced if the new @tail_id would be in the * committed or reusable queried state. This makes it possible that a valid * sequence number of the tail is always available. * * Descriptor Finalization * ~~~~~~~~~~~~~~~~~~~~~~~ * When a writer calls the commit function prb_commit(), record data is * fully stored and is consistent within the ringbuffer. However, a writer can * reopen that record, claiming exclusive access (as with prb_reserve()), and * modify that record. When finished, the writer must again commit the record. * * In order for a record to be made available to readers (and also become * recyclable for writers), it must be finalized. A finalized record cannot be * reopened and can never become "unfinalized". Record finalization can occur * in three different scenarios: * * 1) A writer can simultaneously commit and finalize its record by calling * prb_final_commit() instead of prb_commit(). * * 2) When a new record is reserved and the previous record has been * committed via prb_commit(), that previous record is automatically * finalized. * * 3) When a record is committed via prb_commit() and a newer record * already exists, the record being committed is automatically finalized. * * Data Ring * ~~~~~~~~~ * The text data ring is a byte array composed of data blocks. Data blocks are * referenced by blk_lpos structs that point to the logical position of the * beginning of a data block and the beginning of the next adjacent data * block. Logical positions are mapped directly to index values of the byte * array ringbuffer. * * Each data block consists of an ID followed by the writer data. The ID is * the identifier of a descriptor that is associated with the data block. A * given data block is considered valid if all of the following conditions * are met: * * 1) The descriptor associated with the data block is in the committed * or finalized queried state. * * 2) The blk_lpos struct within the descriptor associated with the data * block references back to the same data block. * * 3) The data block is within the head/tail logical position range. * * If the writer data of a data block would extend beyond the end of the * byte array, only the ID of the data block is stored at the logical * position and the full data block (ID and writer data) is stored at the * beginning of the byte array. The referencing blk_lpos will point to the * ID before the wrap and the next data block will be at the logical * position adjacent the full data block after the wrap. * * Data rings have a @tail_lpos that points to the beginning of the oldest * data block and a @head_lpos that points to the logical position of the * next (not yet existing) data block. * * When a new data block should be created (and the ring is full), tail data * blocks will first be invalidated by putting their associated descriptors * into the reusable state and then pushing the @tail_lpos forward beyond * them. Then the @head_lpos is pushed forward and is associated with a new * descriptor. If a data block is not valid, the @tail_lpos cannot be * advanced beyond it. * * Info Array * ~~~~~~~~~~ * The general meta data of printk records are stored in printk_info structs, * stored in an array with the same number of elements as the descriptor ring. * Each info corresponds to the descriptor of the same index in the * descriptor ring. Info validity is confirmed by evaluating the corresponding * descriptor before and after loading the info. * * Usage * ----- * Here are some simple examples demonstrating writers and readers. For the * examples a global ringbuffer (test_rb) is available (which is not the * actual ringbuffer used by printk):: * * DEFINE_PRINTKRB(test_rb, 15, 5); * * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of * 1 MiB (2 ^ (15 + 5)) for text data. * * Sample writer code:: * * const char *textstr = "message text"; * struct prb_reserved_entry e; * struct printk_record r; * * // specify how much to allocate * prb_rec_init_wr(&r, strlen(textstr) + 1); * * if (prb_reserve(&e, &test_rb, &r)) { * snprintf(r.text_buf, r.text_buf_size, "%s", textstr); * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit and finalize the record * prb_final_commit(&e); * } * * Note that additional writer functions are available to extend a record * after it has been committed but not yet finalized. This can be done as * long as no new records have been reserved and the caller is the same. * * Sample writer code (record extending):: * * // alternate rest of previous example * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit the record (but do not finalize yet) * prb_commit(&e); * } * * ... * * // specify additional 5 bytes text space to extend * prb_rec_init_wr(&r, 5); * * // try to extend, but only if it does not exceed 32 bytes * if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id(), 32)) { * snprintf(&r.text_buf[r.info->text_len], * r.text_buf_size - r.info->text_len, "hello"); * * r.info->text_len += 5; * * // commit and finalize the record * prb_final_commit(&e); * } * * Sample reader code:: * * struct printk_info info; * struct printk_record r; * char text_buf[32]; * u64 seq; * * prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf)); * * prb_for_each_record(0, &test_rb, &seq, &r) { * if (info.seq != seq) * pr_warn("lost %llu records\n", info.seq - seq); * * if (info.text_len > r.text_buf_size) { * pr_warn("record %llu text truncated\n", info.seq); * text_buf[r.text_buf_size - 1] = 0; * } * * pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec, * &text_buf[0]); * } * * Note that additional less convenient reader functions are available to * allow complex record access. * * ABA Issues * ~~~~~~~~~~ * To help avoid ABA issues, descriptors are referenced by IDs (array index * values combined with tagged bits counting array wraps) and data blocks are * referenced by logical positions (array index values combined with tagged * bits counting array wraps). However, on 32-bit systems the number of * tagged bits is relatively small such that an ABA incident is (at least * theoretically) possible. For example, if 4 million maximally sized (1KiB) * printk messages were to occur in NMI context on a 32-bit system, the * interrupted context would not be able to recognize that the 32-bit integer * completely wrapped and thus represents a different data block than the one * the interrupted context expects. * * To help combat this possibility, additional state checking is performed * (such as using cmpxchg() even though set() would suffice). These extra * checks are commented as such and will hopefully catch any ABA issue that * a 32-bit system might experience. * * Memory Barriers * ~~~~~~~~~~~~~~~ * Multiple memory barriers are used. To simplify proving correctness and * generating litmus tests, lines of code related to memory barriers * (loads, stores, and the associated memory barriers) are labeled:: * * LMM(function:letter) * * Comments reference the labels using only the "function:letter" part. * * The memory barrier pairs and their ordering are: * * desc_reserve:D / desc_reserve:B * push descriptor tail (id), then push descriptor head (id) * * desc_reserve:D / data_push_tail:B * push data tail (lpos), then set new descriptor reserved (state) * * desc_reserve:D / desc_push_tail:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:D / prb_first_seq:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:F / desc_read:D * set new descriptor id and reserved (state), then allow writer changes * * data_alloc:A (or data_realloc:A) / desc_read:D * set old descriptor reusable (state), then modify new data block area * * data_alloc:A (or data_realloc:A) / data_push_tail:B * push data tail (lpos), then modify new data block area * * _prb_commit:B / desc_read:B * store writer changes, then set new descriptor committed (state) * * desc_reopen_last:A / _prb_commit:B * set descriptor reserved (state), then read descriptor data * * _prb_commit:B / desc_reserve:D * set new descriptor committed (state), then check descriptor head (id) * * data_push_tail:D / data_push_tail:A * set descriptor reusable (state), then push data tail (lpos) * * desc_push_tail:B / desc_reserve:D * set descriptor reusable (state), then push descriptor tail (id) * * desc_update_last_finalized:A / desc_last_finalized_seq:A * store finalized record, then set new highest finalized sequence number */ #define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) #define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1) #define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits) #define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1) /* Determine the data array index from a logical position. */ #define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring)) /* Determine the desc array index from an ID or sequence number. */ #define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring)) /* Determine how many times the data array has wrapped. */ #define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits) /* Determine if a logical position refers to a data-less block. */ #define LPOS_DATALESS(lpos) ((lpos) & 1UL) #define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \ LPOS_DATALESS((blk)->next)) /* Get the logical position at index 0 of the current wrap. */ #define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \ ((lpos) & ~DATA_SIZE_MASK(data_ring)) /* Get the ID for the same index of the previous wrap as the given ID. */ #define DESC_ID_PREV_WRAP(desc_ring, id) \ DESC_ID((id) - DESCS_COUNT(desc_ring)) /* * A data block: mapped directly to the beginning of the data block area * specified as a logical position within the data ring. * * @id: the ID of the associated descriptor * @data: the writer data * * Note that the size of a data block is only known by its associated * descriptor. */ struct prb_data_block { unsigned long id; char data[]; }; /* * Return the descriptor associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->descs[DESC_INDEX(desc_ring, n)]; } /* * Return the printk_info associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->infos[DESC_INDEX(desc_ring, n)]; } static struct prb_data_block *to_block(struct prb_data_ring *data_ring, unsigned long begin_lpos) { return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)]; } /* * Increase the data size to account for data block meta data plus any * padding so that the adjacent data block is aligned on the ID size. */ static unsigned int to_blk_size(unsigned int size) { struct prb_data_block *db = NULL; size += sizeof(*db); size = ALIGN(size, sizeof(db->id)); return size; } /* * Sanity checker for reserve size. The ringbuffer code assumes that a data * block does not exceed the maximum possible size that could fit within the * ringbuffer. This function provides that basic size check so that the * assumption is safe. */ static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size) { struct prb_data_block *db = NULL; if (size == 0) return true; /* * Ensure the alignment padded size could possibly fit in the data * array. The largest possible data block must still leave room for * at least the ID of the next block. */ size = to_blk_size(size); if (size > DATA_SIZE(data_ring) - sizeof(db->id)) return false; return true; } /* Query the state of a descriptor. */ static enum desc_state get_desc_state(unsigned long id, unsigned long state_val) { if (id != DESC_ID(state_val)) return desc_miss; return DESC_STATE(state_val); } /* * Get a copy of a specified descriptor and return its queried state. If the * descriptor is in an inconsistent state (miss or reserved), the caller can * only expect the descriptor's @state_var field to be valid. * * The sequence number and caller_id can be optionally retrieved. Like all * non-state_var data, they are only valid if the descriptor is in a * consistent state. */ static enum desc_state desc_read(struct prb_desc_ring *desc_ring, unsigned long id, struct prb_desc *desc_out, u64 *seq_out, u32 *caller_id_out) { struct printk_info *info = to_info(desc_ring, id); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; enum desc_state d_state; unsigned long state_val; /* Check the descriptor state. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */ d_state = get_desc_state(id, state_val); if (d_state == desc_miss || d_state == desc_reserved) { /* * The descriptor is in an inconsistent state. Set at least * @state_var so that the caller can see the details of * the inconsistent state. */ goto out; } /* * Guarantee the state is loaded before copying the descriptor * content. This avoids copying obsolete descriptor content that might * not apply to the descriptor state. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_read:A reads from _prb_commit:B, then desc_read:C reads * from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * RMB from desc_read:A to desc_read:C */ smp_rmb(); /* LMM(desc_read:B) */ /* * Copy the descriptor data. The data is not valid until the * state has been re-checked. A memcpy() for all of @desc * cannot be used because of the atomic_t @state_var field. */ if (desc_out) { memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos, sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */ } if (seq_out) *seq_out = info->seq; /* also part of desc_read:C */ if (caller_id_out) *caller_id_out = info->caller_id; /* also part of desc_read:C */ /* * 1. Guarantee the descriptor content is loaded before re-checking * the state. This avoids reading an obsolete descriptor state * that may not apply to the copied content. This pairs with * desc_reserve:F. * * Memory barrier involvement: * * If desc_read:C reads from desc_reserve:G, then desc_read:E * reads from desc_reserve:F. * * Relies on: * * WMB from desc_reserve:F to desc_reserve:G * matching * RMB from desc_read:C to desc_read:E * * 2. Guarantee the record data is loaded before re-checking the * state. This avoids reading an obsolete descriptor state that may * not apply to the copied data. This pairs with data_alloc:A and * data_realloc:A. * * Memory barrier involvement: * * If copy_data:A reads from data_alloc:B, then desc_read:E * reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_alloc:B * matching * RMB from desc_read:C to desc_read:E * * Note: desc_make_reusable:A and data_alloc:B can be different * CPUs. However, the data_alloc:B CPU (which performs the * full memory barrier) must have previously seen * desc_make_reusable:A. */ smp_rmb(); /* LMM(desc_read:D) */ /* * The data has been copied. Return the current descriptor state, * which may have changed since the load above. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */ d_state = get_desc_state(id, state_val); out: if (desc_out) atomic_long_set(&desc_out->state_var, state_val); return d_state; } /* * Take a specified descriptor out of the finalized state by attempting * the transition from finalized to reusable. Either this context or some * other context will have been successful. */ static void desc_make_reusable(struct prb_desc_ring *desc_ring, unsigned long id) { unsigned long val_finalized = DESC_SV(id, desc_finalized); unsigned long val_reusable = DESC_SV(id, desc_reusable); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; atomic_long_cmpxchg_relaxed(state_var, val_finalized, val_reusable); /* LMM(desc_make_reusable:A) */ } /* * Given the text data ring, put the associated descriptor of each * data block from @lpos_begin until @lpos_end into the reusable state. * * If there is any problem making the associated descriptor reusable, either * the descriptor has not yet been finalized or another writer context has * already pushed the tail lpos past the problematic data block. Regardless, * on error the caller can re-load the tail lpos to determine the situation. */ static bool data_make_reusable(struct printk_ringbuffer *rb, unsigned long lpos_begin, unsigned long lpos_end, unsigned long *lpos_out) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_desc_ring *desc_ring = &rb->desc_ring; struct prb_data_block *blk; enum desc_state d_state; struct prb_desc desc; struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos; unsigned long id; /* Loop until @lpos_begin has advanced to or beyond @lpos_end. */ while ((lpos_end - lpos_begin) - 1 < DATA_SIZE(data_ring)) { blk = to_block(data_ring, lpos_begin); /* * Load the block ID from the data block. This is a data race * against a writer that may have newly reserved this data * area. If the loaded value matches a valid descriptor ID, * the blk_lpos of that descriptor will be checked to make * sure it points back to this data block. If the check fails, * the data area has been recycled by another writer. */ id = blk->id; /* LMM(data_make_reusable:A) */ d_state = desc_read(desc_ring, id, &desc, NULL, NULL); /* LMM(data_make_reusable:B) */ switch (d_state) { case desc_miss: case desc_reserved: case desc_committed: return false; case desc_finalized: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; desc_make_reusable(desc_ring, id); break; case desc_reusable: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; break; } /* Advance @lpos_begin to the next data block. */ lpos_begin = blk_lpos->next; } *lpos_out = lpos_begin; return true; } /* * Advance the data ring tail to at least @lpos. This function puts * descriptors into the reusable state if the tail is pushed beyond * their associated data block. */ static bool data_push_tail(struct printk_ringbuffer *rb, unsigned long lpos) { struct prb_data_ring *data_ring = &rb->text_data_ring; unsigned long tail_lpos_new; unsigned long tail_lpos; unsigned long next_lpos; /* If @lpos is from a data-less block, there is nothing to do. */ if (LPOS_DATALESS(lpos)) return true; /* * Any descriptor states that have transitioned to reusable due to the * data tail being pushed to this loaded value will be visible to this * CPU. This pairs with data_push_tail:D. * * Memory barrier involvement: * * If data_push_tail:A reads from data_push_tail:D, then this CPU can * see desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_push_tail:D * matches * READFROM from data_push_tail:D to data_push_tail:A * thus * READFROM from desc_make_reusable:A to this CPU */ tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */ /* * Loop until the tail lpos is at or beyond @lpos. This condition * may already be satisfied, resulting in no full memory barrier * from data_push_tail:D being performed. However, since this CPU * sees the new tail lpos, any descriptor states that transitioned to * the reusable state must already be visible. */ while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) { /* * Make all descriptors reusable that are associated with * data blocks before @lpos. */ if (!data_make_reusable(rb, tail_lpos, lpos, &next_lpos)) { /* * 1. Guarantee the block ID loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled data area causing the tail lpos to * have been previously pushed. This pairs with * data_alloc:A and data_realloc:A. * * Memory barrier involvement: * * If data_make_reusable:A reads from data_alloc:B, * then data_push_tail:C reads from * data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to data_alloc:B * matching * RMB from data_make_reusable:A to * data_push_tail:C * * Note: data_push_tail:D and data_alloc:B can be * different CPUs. However, the data_alloc:B * CPU (which performs the full memory * barrier) must have previously seen * data_push_tail:D. * * 2. Guarantee the descriptor state loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled descriptor causing the tail lpos to * have been previously pushed. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If data_make_reusable:B reads from * desc_reserve:F, then data_push_tail:C reads * from data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to desc_reserve:F * matching * RMB from data_make_reusable:B to * data_push_tail:C * * Note: data_push_tail:D and desc_reserve:F can * be different CPUs. However, the * desc_reserve:F CPU (which performs the * full memory barrier) must have previously * seen data_push_tail:D. */ smp_rmb(); /* LMM(data_push_tail:B) */ tail_lpos_new = atomic_long_read(&data_ring->tail_lpos ); /* LMM(data_push_tail:C) */ if (tail_lpos_new == tail_lpos) return false; /* Another CPU pushed the tail. Try again. */ tail_lpos = tail_lpos_new; continue; } /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail lpos. A full * memory barrier is needed since other CPUs may have made * the descriptor states reusable. This pairs with * data_push_tail:A. */ if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos, next_lpos)) { /* LMM(data_push_tail:D) */ break; } } return true; } /* * Advance the desc ring tail. This function advances the tail by one * descriptor, thus invalidating the oldest descriptor. Before advancing * the tail, the tail descriptor is made reusable and all data blocks up to * and including the descriptor's data block are invalidated (i.e. the data * ring tail is pushed past the data block of the descriptor being made * reusable). */ static bool desc_push_tail(struct printk_ringbuffer *rb, unsigned long tail_id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL); switch (d_state) { case desc_miss: /* * If the ID is exactly 1 wrap behind the expected, it is * in the process of being reserved by another writer and * must be considered reserved. */ if (DESC_ID(atomic_long_read(&desc.state_var)) == DESC_ID_PREV_WRAP(desc_ring, tail_id)) { return false; } /* * The ID has changed. Another writer must have pushed the * tail and recycled the descriptor already. Success is * returned because the caller is only interested in the * specified tail being pushed, which it was. */ return true; case desc_reserved: case desc_committed: return false; case desc_finalized: desc_make_reusable(desc_ring, tail_id); break; case desc_reusable: break; } /* * Data blocks must be invalidated before their associated * descriptor can be made available for recycling. Invalidating * them later is not possible because there is no way to trust * data blocks once their associated descriptor is gone. */ if (!data_push_tail(rb, desc.text_blk_lpos.next)) return false; /* * Check the next descriptor after @tail_id before pushing the tail * to it because the tail must always be in a finalized or reusable * state. The implementation of prb_first_seq() relies on this. * * A successful read implies that the next descriptor is less than or * equal to @head_id so there is no risk of pushing the tail past the * head. */ d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc, NULL, NULL); /* LMM(desc_push_tail:A) */ if (d_state == desc_finalized || d_state == desc_reusable) { /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail ID. This allows * verifying the recycled descriptor state. A full memory * barrier is needed since other CPUs may have made the * descriptor states reusable. This pairs with desc_reserve:D. */ atomic_long_cmpxchg(&desc_ring->tail_id, tail_id, DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */ } else { /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail ID in the * case that the descriptor has been recycled. This pairs * with desc_reserve:D. * * Memory barrier involvement: * * If desc_push_tail:A reads from desc_reserve:F, then * desc_push_tail:D reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB from desc_push_tail:A to desc_push_tail:D * * Note: desc_push_tail:B and desc_reserve:F can be different * CPUs. However, the desc_reserve:F CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_push_tail:C) */ /* * Re-check the tail ID. The descriptor following @tail_id is * not in an allowed tail state. But if the tail has since * been moved by another CPU, then it does not matter. */ if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */ return false; } return true; } /* Reserve a new descriptor, invalidating the oldest if necessary. */ static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val; unsigned long id_prev_wrap; struct prb_desc *desc; unsigned long head_id; unsigned long id; head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ do { id = DESC_ID(head_id + 1); id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); /* * Guarantee the head ID is read before reading the tail ID. * Since the tail ID is updated before the head ID, this * guarantees that @id_prev_wrap is never ahead of the tail * ID. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If desc_reserve:A reads from desc_reserve:D, then * desc_reserve:C reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:D * matching * RMB from desc_reserve:A to desc_reserve:C * * Note: desc_push_tail:B and desc_reserve:D can be different * CPUs. However, the desc_reserve:D CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_reserve:B) */ if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id )) { /* LMM(desc_reserve:C) */ /* * Make space for the new descriptor by * advancing the tail. */ if (!desc_push_tail(rb, id_prev_wrap)) return false; } /* * 1. Guarantee the tail ID is read before validating the * recycled descriptor state. A read memory barrier is * sufficient for this. This pairs with desc_push_tail:B. * * Memory barrier involvement: * * If desc_reserve:C reads from desc_push_tail:B, then * desc_reserve:E reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to desc_push_tail:B * matching * RMB from desc_reserve:C to desc_reserve:E * * Note: desc_make_reusable:A and desc_push_tail:B can be * different CPUs. However, the desc_push_tail:B CPU * (which performs the full memory barrier) must have * previously seen desc_make_reusable:A. * * 2. Guarantee the tail ID is stored before storing the head * ID. This pairs with desc_reserve:B. * * 3. Guarantee any data ring tail changes are stored before * recycling the descriptor. Data ring tail changes can * happen via desc_push_tail()->data_push_tail(). A full * memory barrier is needed since another CPU may have * pushed the data ring tails. This pairs with * data_push_tail:B. * * 4. Guarantee a new tail ID is stored before recycling the * descriptor. A full memory barrier is needed since * another CPU may have pushed the tail ID. This pairs * with desc_push_tail:C and this also pairs with * prb_first_seq:C. * * 5. Guarantee the head ID is stored before trying to * finalize the previous descriptor. This pairs with * _prb_commit:B. */ } while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id, id)); /* LMM(desc_reserve:D) */ desc = to_desc(desc_ring, id); /* * If the descriptor has been recycled, verify the old state val. * See "ABA Issues" about why this verification is performed. */ prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */ if (prev_state_val && get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) { WARN_ON_ONCE(1); return false; } /* * Assign the descriptor a new ID and set its state to reserved. * See "ABA Issues" about why cmpxchg() instead of set() is used. * * Guarantee the new descriptor ID and state is stored before making * any other changes. A write memory barrier is sufficient for this. * This pairs with desc_read:D. */ if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */ WARN_ON_ONCE(1); return false; } /* Now data in @desc can be modified: LMM(desc_reserve:G) */ *id_out = id; return true; } /* Determine the end of a data block. */ static unsigned long get_next_lpos(struct prb_data_ring *data_ring, unsigned long lpos, unsigned int size) { unsigned long begin_lpos; unsigned long next_lpos; begin_lpos = lpos; next_lpos = lpos + size; /* First check if the data block does not wrap. */ if (DATA_WRAPS(data_ring, begin_lpos) == DATA_WRAPS(data_ring, next_lpos)) return next_lpos; /* Wrapping data blocks store their data at the beginning. */ return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size); } /* * Allocate a new data block, invalidating the oldest data block(s) * if necessary. This function also associates the data block with * a specified descriptor. */ static char *data_alloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long begin_lpos; unsigned long next_lpos; if (size == 0) { /* * Data blocks are not created for empty lines. Instead, the * reader will recognize these special lpos values and handle * it appropriately. */ blk_lpos->begin = EMPTY_LINE_LPOS; blk_lpos->next = EMPTY_LINE_LPOS; return NULL; } size = to_blk_size(size); begin_lpos = atomic_long_read(&data_ring->head_lpos); do { next_lpos = get_next_lpos(data_ring, begin_lpos, size); if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) { /* Failed to allocate, specify a data-less block. */ blk_lpos->begin = FAILED_LPOS; blk_lpos->next = FAILED_LPOS; return NULL; } /* * 1. Guarantee any descriptor states that have transitioned * to reusable are stored before modifying the newly * allocated data area. A full memory barrier is needed * since other CPUs may have made the descriptor states * reusable. See data_push_tail:A about why the reusable * states are visible. This pairs with desc_read:D. * * 2. Guarantee any updated tail lpos is stored before * modifying the newly allocated data area. Another CPU may * be in data_make_reusable() and is reading a block ID * from this area. data_make_reusable() can handle reading * a garbage block ID value, but then it must be able to * load a new tail lpos. A full memory barrier is needed * since other CPUs may have updated the tail lpos. This * pairs with data_push_tail:B. */ } while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos, next_lpos)); /* LMM(data_alloc:A) */ blk = to_block(data_ring, begin_lpos); blk->id = id; /* LMM(data_alloc:B) */ if (DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos)) { /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; } blk_lpos->begin = begin_lpos; blk_lpos->next = next_lpos; return &blk->data[0]; } /* * Try to resize an existing data block associated with the descriptor * specified by @id. If the resized data block should become wrapped, it * copies the old data to the new data block. If @size yields a data block * with the same or less size, the data block is left as is. * * Fail if this is not the last allocated data block or if there is not * enough space or it is not possible make enough space. * * Return a pointer to the beginning of the entire data buffer or NULL on * failure. */ static char *data_realloc(struct printk_ringbuffer *rb, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_ring *data_ring = &rb->text_data_ring; struct prb_data_block *blk; unsigned long head_lpos; unsigned long next_lpos; bool wrapped; /* Reallocation only works if @blk_lpos is the newest data block. */ head_lpos = atomic_long_read(&data_ring->head_lpos); if (head_lpos != blk_lpos->next) return NULL; /* Keep track if @blk_lpos was a wrapping data block. */ wrapped = (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, blk_lpos->next)); size = to_blk_size(size); next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size); /* If the data block does not increase, there is nothing to do. */ if (head_lpos - next_lpos < DATA_SIZE(data_ring)) { if (wrapped) blk = to_block(data_ring, 0); else blk = to_block(data_ring, blk_lpos->begin); return &blk->data[0]; } if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) return NULL; /* The memory barrier involvement is the same as data_alloc:A. */ if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos, next_lpos)) { /* LMM(data_realloc:A) */ return NULL; } blk = to_block(data_ring, blk_lpos->begin); if (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, next_lpos)) { struct prb_data_block *old_blk = blk; /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; if (!wrapped) { /* * Since the allocated space is now in the newly * created wrapping data block, copy the content * from the old data block. */ memcpy(&blk->data[0], &old_blk->data[0], (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id)); } } blk_lpos->next = next_lpos; return &blk->data[0]; } /* Return the number of bytes used by a data block. */ static unsigned int space_used(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos) { /* Data-less blocks take no space. */ if (BLK_DATALESS(blk_lpos)) return 0; if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next)) { /* Data block does not wrap. */ return (DATA_INDEX(data_ring, blk_lpos->next) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * For wrapping data blocks, the trailing (wasted) space is * also counted. */ return (DATA_INDEX(data_ring, blk_lpos->next) + DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * Given @blk_lpos, return a pointer to the writer data from the data block * and calculate the size of the data part. A NULL pointer is returned if * @blk_lpos specifies values that could never be legal. * * This function (used by readers) performs strict validation on the lpos * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static const char *get_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, unsigned int *data_size) { struct prb_data_block *db; /* Data-less data block description. */ if (BLK_DATALESS(blk_lpos)) { /* * Records that are just empty lines are also valid, even * though they do not have a data block. For such records * explicitly return empty string data to signify success. */ if (blk_lpos->begin == EMPTY_LINE_LPOS && blk_lpos->next == EMPTY_LINE_LPOS) { *data_size = 0; return ""; } /* Data lost, invalid, or otherwise unavailable. */ return NULL; } /* Regular data block: @begin less than @next and in same wrap. */ if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next) && blk_lpos->begin < blk_lpos->next) { db = to_block(data_ring, blk_lpos->begin); *data_size = blk_lpos->next - blk_lpos->begin; /* Wrapping data block: @begin is one wrap behind @next. */ } else if (DATA_WRAPS(data_ring, blk_lpos->begin + DATA_SIZE(data_ring)) == DATA_WRAPS(data_ring, blk_lpos->next)) { db = to_block(data_ring, 0); *data_size = DATA_INDEX(data_ring, blk_lpos->next); /* Illegal block description. */ } else { WARN_ON_ONCE(1); return NULL; } /* A valid data block will always be aligned to the ID size. */ if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) { return NULL; } /* A valid data block will always have at least an ID. */ if (WARN_ON_ONCE(*data_size < sizeof(db->id))) return NULL; /* Subtract block ID space from size to reflect data size. */ *data_size -= sizeof(db->id); return &db->data[0]; } /* * Attempt to transition the newest descriptor from committed back to reserved * so that the record can be modified by a writer again. This is only possible * if the descriptor is not yet finalized and the provided @caller_id matches. */ static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring, u32 caller_id, unsigned long *id_out) { unsigned long prev_state_val; enum desc_state d_state; struct prb_desc desc; struct prb_desc *d; unsigned long id; u32 cid; id = atomic_long_read(&desc_ring->head_id); /* * To reduce unnecessarily reopening, first check if the descriptor * state and caller ID are correct. */ d_state = desc_read(desc_ring, id, &desc, NULL, &cid); if (d_state != desc_committed || cid != caller_id) return NULL; d = to_desc(desc_ring, id); prev_state_val = DESC_SV(id, desc_committed); /* * Guarantee the reserved state is stored before reading any * record data. A full memory barrier is needed because @state_var * modification is followed by reading. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_reopen_last:A reads from _prb_commit:B, then * prb_reserve_in_last:A reads from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * MB If desc_reopen_last:A to prb_reserve_in_last:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */ return NULL; } *id_out = id; return d; } /** * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer * used by the newest record. * * @e: The entry structure to setup. * @rb: The ringbuffer to re-reserve and extend data in. * @r: The record structure to allocate buffers for. * @caller_id: The caller ID of the caller (reserving writer). * @max_size: Fail if the extended size would be greater than this. * * This is the public function available to writers to re-reserve and extend * data. * * The writer specifies the text size to extend (not the new total size) by * setting the @text_buf_size field of @r. To ensure proper initialization * of @r, prb_rec_init_wr() should be used. * * This function will fail if @caller_id does not match the caller ID of the * newest record. In that case the caller must reserve new data using * prb_reserve(). * * Context: Any context. Disables local interrupts on success. * Return: true if text data could be extended, otherwise false. * * On success: * * - @r->text_buf points to the beginning of the entire text buffer. * * - @r->text_buf_size is set to the new total size of the buffer. * * - @r->info is not touched so that @r->info->text_len could be used * to append the text. * * - prb_record_text_space() can be used on @e to query the new * actually used space. * * Important: All @r->info fields will already be set with the current values * for the record. I.e. @r->info->text_len will be less than * @text_buf_size. Writers can use @r->info->text_len to know * where concatenation begins and writers should update * @r->info->text_len after concatenating. */ bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; unsigned int data_size; struct prb_desc *d; unsigned long id; local_irq_save(e->irqflags); /* Transition the newest descriptor back to the reserved state. */ d = desc_reopen_last(desc_ring, caller_id, &id); if (!d) { local_irq_restore(e->irqflags); goto fail_reopen; } /* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */ info = to_info(desc_ring, id); /* * Set the @e fields here so that prb_commit() can be used if * anything fails from now on. */ e->rb = rb; e->id = id; /* * desc_reopen_last() checked the caller_id, but there was no * exclusive access at that point. The descriptor may have * changed since then. */ if (caller_id != info->caller_id) goto fail; if (BLK_DATALESS(&d->text_blk_lpos)) { if (WARN_ON_ONCE(info->text_len != 0)) { pr_warn_once("wrong text_len value (%hu, expecting 0)\n", info->text_len); info->text_len = 0; } if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } else { if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size)) goto fail; /* * Increase the buffer size to include the original size. If * the meta data (@text_len) is not sane, use the full data * block size. */ if (WARN_ON_ONCE(info->text_len > data_size)) { pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n", info->text_len, data_size); info->text_len = data_size; } r->text_buf_size += info->text_len; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_realloc(rb, r->text_buf_size, &d->text_blk_lpos, id); } if (r->text_buf_size && !r->text_buf) goto fail; r->info = info; e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: prb_commit(e); /* prb_commit() re-enabled interrupts. */ fail_reopen: /* Make it clear to the caller that the re-reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* * @last_finalized_seq value guarantees that all records up to and including * this sequence number are finalized and can be read. The only exception are * too old records which have already been overwritten. * * It is also guaranteed that @last_finalized_seq only increases. * * Be aware that finalized records following non-finalized records are not * reported because they are not yet available to the reader. For example, * a new record stored via printk() will not be available to a printer if * it follows a record that has not been finalized yet. However, once that * non-finalized record becomes finalized, @last_finalized_seq will be * appropriately updated and the full set of finalized records will be * available to the printer. And since each printk() caller will either * directly print or trigger deferred printing of all available unprinted * records, all printk() messages will get printed. */ static u64 desc_last_finalized_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long ulseq; /* * Guarantee the sequence number is loaded before loading the * associated record in order to guarantee that the record can be * seen by this CPU. This pairs with desc_update_last_finalized:A. */ ulseq = atomic_long_read_acquire(&desc_ring->last_finalized_seq ); /* LMM(desc_last_finalized_seq:A) */ return __ulseq_to_u64seq(rb, ulseq); } static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count); /* * Check if there are records directly following @last_finalized_seq that are * finalized. If so, update @last_finalized_seq to the latest of these * records. It is not allowed to skip over records that are not yet finalized. */ static void desc_update_last_finalized(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; u64 old_seq = desc_last_finalized_seq(rb); unsigned long oldval; unsigned long newval; u64 finalized_seq; u64 try_seq; try_again: finalized_seq = old_seq; try_seq = finalized_seq + 1; /* Try to find later finalized records. */ while (_prb_read_valid(rb, &try_seq, NULL, NULL)) { finalized_seq = try_seq; try_seq++; } /* No update needed if no later finalized record was found. */ if (finalized_seq == old_seq) return; oldval = __u64seq_to_ulseq(old_seq); newval = __u64seq_to_ulseq(finalized_seq); /* * Set the sequence number of a later finalized record that has been * seen. * * Guarantee the record data is visible to other CPUs before storing * its sequence number. This pairs with desc_last_finalized_seq:A. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then desc_read:A reads from * _prb_commit:B. * * Relies on: * * RELEASE from _prb_commit:B to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to desc_read:A * * Note: _prb_commit:B and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A * CPU (which performs the release) must have previously seen * _prb_commit:B. */ if (!atomic_long_try_cmpxchg_release(&desc_ring->last_finalized_seq, &oldval, newval)) { /* LMM(desc_update_last_finalized:A) */ old_seq = __ulseq_to_u64seq(rb, oldval); goto try_again; } } /* * Attempt to finalize a specified descriptor. If this fails, the descriptor * is either already final or it will finalize itself when the writer commits. */ static void desc_make_final(struct printk_ringbuffer *rb, unsigned long id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val = DESC_SV(id, desc_committed); struct prb_desc *d = to_desc(desc_ring, id); if (atomic_long_try_cmpxchg_relaxed(&d->state_var, &prev_state_val, DESC_SV(id, desc_finalized))) { /* LMM(desc_make_final:A) */ desc_update_last_finalized(rb); } } /** * prb_reserve() - Reserve space in the ringbuffer. * * @e: The entry structure to setup. * @rb: The ringbuffer to reserve data in. * @r: The record structure to allocate buffers for. * * This is the public function available to writers to reserve data. * * The writer specifies the text size to reserve by setting the * @text_buf_size field of @r. To ensure proper initialization of @r, * prb_rec_init_wr() should be used. * * Context: Any context. Disables local interrupts on success. * Return: true if at least text data could be allocated, otherwise false. * * On success, the fields @info and @text_buf of @r will be set by this * function and should be filled in by the writer before committing. Also * on success, prb_record_text_space() can be used on @e to query the actual * space used for the text data block. * * Important: @info->text_len needs to be set correctly by the writer in * order for data to be readable and/or extended. Its value * is initialized to 0. */ bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; struct prb_desc *d; unsigned long id; u64 seq; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; /* * Descriptors in the reserved state act as blockers to all further * reservations once the desc_ring has fully wrapped. Disable * interrupts during the reserve/commit window in order to minimize * the likelihood of this happening. */ local_irq_save(e->irqflags); if (!desc_reserve(rb, &id)) { /* Descriptor reservation failures are tracked. */ atomic_long_inc(&rb->fail); local_irq_restore(e->irqflags); goto fail; } d = to_desc(desc_ring, id); info = to_info(desc_ring, id); /* * All @info fields (except @seq) are cleared and must be filled in * by the writer. Save @seq before clearing because it is used to * determine the new sequence number. */ seq = info->seq; memset(info, 0, sizeof(*info)); /* * Set the @e fields here so that prb_commit() can be used if * text data allocation fails. */ e->rb = rb; e->id = id; /* * Initialize the sequence number if it has "never been set". * Otherwise just increment it by a full wrap. * * @seq is considered "never been set" if it has a value of 0, * _except_ for @infos[0], which was specially setup by the ringbuffer * initializer and therefore is always considered as set. * * See the "Bootstrap" comment block in printk_ringbuffer.h for * details about how the initializer bootstraps the descriptors. */ if (seq == 0 && DESC_INDEX(desc_ring, id) != 0) info->seq = DESC_INDEX(desc_ring, id); else info->seq = seq + DESCS_COUNT(desc_ring); /* * New data is about to be reserved. Once that happens, previous * descriptors are no longer able to be extended. Finalize the * previous descriptor now so that it can be made available to * readers. (For seq==0 there is no previous descriptor.) */ if (info->seq > 0) desc_make_final(rb, DESC_ID(id - 1)); r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); /* If text data allocation fails, a data-less record is committed. */ if (r->text_buf_size && !r->text_buf) { prb_commit(e); /* prb_commit() re-enabled interrupts. */ goto fail; } r->info = info; /* Record full text space used by record. */ e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: /* Make it clear to the caller that the reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* Commit the data (possibly finalizing it) and restore interrupts. */ static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; struct prb_desc *d = to_desc(desc_ring, e->id); unsigned long prev_state_val = DESC_SV(e->id, desc_reserved); /* Now the writer has finished all writing: LMM(_prb_commit:A) */ /* * Set the descriptor as committed. See "ABA Issues" about why * cmpxchg() instead of set() is used. * * 1 Guarantee all record data is stored before the descriptor state * is stored as committed. A write memory barrier is sufficient * for this. This pairs with desc_read:B and desc_reopen_last:A. * * 2. Guarantee the descriptor state is stored as committed before * re-checking the head ID in order to possibly finalize this * descriptor. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If prb_commit:A reads from desc_reserve:D, then * desc_make_final:A reads from _prb_commit:B. * * Relies on: * * MB _prb_commit:B to prb_commit:A * matching * MB desc_reserve:D to desc_make_final:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */ WARN_ON_ONCE(1); } /* Restore interrupts, the reserve/commit window is finished. */ local_irq_restore(e->irqflags); } /** * prb_commit() - Commit (previously reserved) data to the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit data. * * Note that the data is not yet available to readers until it is finalized. * Finalizing happens automatically when space for the next record is * reserved. * * See prb_final_commit() for a version of this function that finalizes * immediately. * * Context: Any context. Enables local interrupts. */ void prb_commit(struct prb_reserved_entry *e) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; unsigned long head_id; _prb_commit(e, desc_committed); /* * If this descriptor is no longer the head (i.e. a new record has * been allocated), extending the data for this record is no longer * allowed and therefore it must be finalized. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ if (head_id != e->id) desc_make_final(e->rb, e->id); } /** * prb_final_commit() - Commit and finalize (previously reserved) data to * the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit+finalize data. * * By finalizing, the data is made immediately available to readers. * * This function should only be used if there are no intentions of extending * this data using prb_reserve_in_last(). * * Context: Any context. Enables local interrupts. */ void prb_final_commit(struct prb_reserved_entry *e) { _prb_commit(e, desc_finalized); desc_update_last_finalized(e->rb); } /* * Count the number of lines in provided text. All text has at least 1 line * (even if @text_size is 0). Each '\n' processed is counted as an additional * line. */ static unsigned int count_lines(const char *text, unsigned int text_size) { unsigned int next_size = text_size; unsigned int line_count = 1; const char *next = text; while (next_size) { next = memchr(next, '\n', next_size); if (!next) break; line_count++; next++; next_size = text_size - (next - text); } return line_count; } /* * Given @blk_lpos, copy an expected @len of data into the provided buffer. * If @line_count is provided, count the number of lines in the data. * * This function (used by readers) performs strict validation on the data * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static bool copy_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf, unsigned int buf_size, unsigned int *line_count) { unsigned int data_size; const char *data; /* Caller might not want any data. */ if ((!buf || !buf_size) && !line_count) return true; data = get_data(data_ring, blk_lpos, &data_size); if (!data) return false; /* * Actual cannot be less than expected. It can be more than expected * because of the trailing alignment padding. * * Note that invalid @len values can occur because the caller loads * the value during an allowed data race. */ if (data_size < (unsigned int)len) return false; /* Caller interested in the line count? */ if (line_count) *line_count = count_lines(data, len); /* Caller interested in the data content? */ if (!buf || !buf_size) return true; data_size = min_t(unsigned int, buf_size, len); memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ return true; } /* * This is an extended version of desc_read(). It gets a copy of a specified * descriptor. However, it also verifies that the record is finalized and has * the sequence number @seq. On success, 0 is returned. * * Error return values: * -EINVAL: A finalized record with sequence number @seq does not exist. * -ENOENT: A finalized record with sequence number @seq exists, but its data * is not available. This is a valid record, so readers should * continue with the next record. */ static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring, unsigned long id, u64 seq, struct prb_desc *desc_out) { struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos; enum desc_state d_state; u64 s; d_state = desc_read(desc_ring, id, desc_out, &s, NULL); /* * An unexpected @id (desc_miss) or @seq mismatch means the record * does not exist. A descriptor in the reserved or committed state * means the record does not yet exist for the reader. */ if (d_state == desc_miss || d_state == desc_reserved || d_state == desc_committed || s != seq) { return -EINVAL; } /* * A descriptor in the reusable state may no longer have its data * available; report it as existing but with lost data. Or the record * may actually be a record with lost data. */ if (d_state == desc_reusable || (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) { return -ENOENT; } return 0; } /* * Copy the ringbuffer data from the record with @seq to the provided * @r buffer. On success, 0 is returned. * * See desc_read_finalized_seq() for error return values. */ static int prb_read(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r, unsigned int *line_count) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info = to_info(desc_ring, seq); struct prb_desc *rdesc = to_desc(desc_ring, seq); atomic_long_t *state_var = &rdesc->state_var; struct prb_desc desc; unsigned long id; int err; /* Extract the ID, used to specify the descriptor to read. */ id = DESC_ID(atomic_long_read(state_var)); /* Get a local copy of the correct descriptor (if available). */ err = desc_read_finalized_seq(desc_ring, id, seq, &desc); /* * If @r is NULL, the caller is only interested in the availability * of the record. */ if (err || !r) return err; /* If requested, copy meta data. */ if (r->info) memcpy(r->info, info, sizeof(*(r->info))); /* Copy text data. If it fails, this is a data-less record. */ if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len, r->text_buf, r->text_buf_size, line_count)) { return -ENOENT; } /* Ensure the record is still finalized and has the same @seq. */ return desc_read_finalized_seq(desc_ring, id, seq, &desc); } /* Get the sequence number of the tail descriptor. */ u64 prb_first_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; unsigned long id; u64 seq; for (;;) { id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */ d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */ /* * This loop will not be infinite because the tail is * _always_ in the finalized or reusable state. */ if (d_state == desc_finalized || d_state == desc_reusable) break; /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail in the case * that the descriptor has been recycled. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If prb_first_seq:B reads from desc_reserve:F, then * prb_first_seq:A reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB prb_first_seq:B to prb_first_seq:A */ smp_rmb(); /* LMM(prb_first_seq:C) */ } return seq; } /** * prb_next_reserve_seq() - Get the sequence number after the most recently * reserved record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what sequence * number will be assigned to the next reserved record. * * Note that depending on the situation, this value can be equal to or * higher than the sequence number returned by prb_next_seq(). * * Context: Any context. * Return: The sequence number that will be assigned to the next record * reserved. */ u64 prb_next_reserve_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long last_finalized_id; atomic_long_t *state_var; u64 last_finalized_seq; unsigned long head_id; struct prb_desc desc; unsigned long diff; struct prb_desc *d; int err; /* * It may not be possible to read a sequence number for @head_id. * So the ID of @last_finailzed_seq is used to calculate what the * sequence number of @head_id will be. */ try_again: last_finalized_seq = desc_last_finalized_seq(rb); /* * @head_id is loaded after @last_finalized_seq to ensure that * it points to the record with @last_finalized_seq or newer. * * Memory barrier involvement: * * If desc_last_finalized_seq:A reads from * desc_update_last_finalized:A, then * prb_next_reserve_seq:A reads from desc_reserve:D. * * Relies on: * * RELEASE from desc_reserve:D to desc_update_last_finalized:A * matching * ACQUIRE from desc_last_finalized_seq:A to prb_next_reserve_seq:A * * Note: desc_reserve:D and desc_update_last_finalized:A can be * different CPUs. However, the desc_update_last_finalized:A CPU * (which performs the release) must have previously seen * desc_read:C, which implies desc_reserve:D can be seen. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_next_reserve_seq:A) */ d = to_desc(desc_ring, last_finalized_seq); state_var = &d->state_var; /* Extract the ID, used to specify the descriptor to read. */ last_finalized_id = DESC_ID(atomic_long_read(state_var)); /* Ensure @last_finalized_id is correct. */ err = desc_read_finalized_seq(desc_ring, last_finalized_id, last_finalized_seq, &desc); if (err == -EINVAL) { if (last_finalized_seq == 0) { /* * No record has been finalized or even reserved yet. * * The @head_id is initialized such that the first * increment will yield the first record (seq=0). * Handle it separately to avoid a negative @diff * below. */ if (head_id == DESC0_ID(desc_ring->count_bits)) return 0; /* * One or more descriptors are already reserved. Use * the descriptor ID of the first one (@seq=0) for * the @diff below. */ last_finalized_id = DESC0_ID(desc_ring->count_bits) + 1; } else { /* Record must have been overwritten. Try again. */ goto try_again; } } /* Diff of known descriptor IDs to compute related sequence numbers. */ diff = head_id - last_finalized_id; /* * @head_id points to the most recently reserved record, but this * function returns the sequence number that will be assigned to the * next (not yet reserved) record. Thus +1 is needed. */ return (last_finalized_seq + diff + 1); } /* * Non-blocking read of a record. * * On success @seq is updated to the record that was read and (if provided) * @r and @line_count will contain the read/calculated data. * * On failure @seq is updated to a record that is not yet available to the * reader, but it will be the next record available to the reader. * * Note: When the current CPU is in panic, this function will skip over any * non-existent/non-finalized records in order to allow the panic CPU * to print any and all records that have been finalized. */ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count) { u64 tail_seq; int err; while ((err = prb_read(rb, *seq, r, line_count))) { tail_seq = prb_first_seq(rb); if (*seq < tail_seq) { /* * Behind the tail. Catch up and try again. This * can happen for -ENOENT and -EINVAL cases. */ *seq = tail_seq; } else if (err == -ENOENT) { /* Record exists, but the data was lost. Skip. */ (*seq)++; } else { /* * Non-existent/non-finalized record. Must stop. * * For panic situations it cannot be expected that * non-finalized records will become finalized. But * there may be other finalized records beyond that * need to be printed for a panic situation. If this * is the panic CPU, skip this * non-existent/non-finalized record unless it is * at or beyond the head, in which case it is not * possible to continue. * * Note that new messages printed on panic CPU are * finalized when we are here. The only exception * might be the last message without trailing newline. * But it would have the sequence number returned * by "prb_next_reserve_seq() - 1". */ if (this_cpu_in_panic() && ((*seq + 1) < prb_next_reserve_seq(rb))) (*seq)++; else return false; } } return true; } /** * prb_read_valid() - Non-blocking read of a requested record or (if gone) * the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @r: A record data buffer to store the read record to. * * This is the public function available to readers to read a record. * * The reader provides the @info and @text_buf buffers of @r to be * filled in. Any of the buffer pointers can be set to NULL if the reader * is not interested in that data. To ensure proper initialization of @r, * prb_rec_init_rd() should be used. * * Context: Any context. * Return: true if a record was read, otherwise false. * * On success, the reader must check r->info.seq to see which record was * actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r) { return _prb_read_valid(rb, &seq, r, NULL); } /** * prb_read_valid_info() - Non-blocking read of meta data for a requested * record or (if gone) the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @info: A buffer to store the read record meta data to. * @line_count: A buffer to store the number of lines in the record text. * * This is the public function available to readers to read only the * meta data of a record. * * The reader provides the @info, @line_count buffers to be filled in. * Either of the buffer pointers can be set to NULL if the reader is not * interested in that data. * * Context: Any context. * Return: true if a record's meta data was read, otherwise false. * * On success, the reader must check info->seq to see which record meta data * was actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count) { struct printk_record r; prb_rec_init_rd(&r, info, NULL, 0); return _prb_read_valid(rb, &seq, &r, line_count); } /** * prb_first_valid_seq() - Get the sequence number of the oldest available * record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the * first/oldest valid sequence number is. * * This provides readers a starting point to begin iterating the ringbuffer. * * Context: Any context. * Return: The sequence number of the first/oldest record or, if the * ringbuffer is empty, 0 is returned. */ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) { u64 seq = 0; if (!_prb_read_valid(rb, &seq, NULL, NULL)) return 0; return seq; } /** * prb_next_seq() - Get the sequence number after the last available record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the next * newest sequence number available to readers will be. * * This provides readers a sequence number to jump to if all currently * available records should be skipped. It is guaranteed that all records * previous to the returned value have been finalized and are (or were) * available to the reader. * * Context: Any context. * Return: The sequence number of the next newest (not yet available) record * for readers. */ u64 prb_next_seq(struct printk_ringbuffer *rb) { u64 seq; seq = desc_last_finalized_seq(rb); /* * Begin searching after the last finalized record. * * On 0, the search must begin at 0 because of hack#2 * of the bootstrapping phase it is not known if a * record at index 0 exists. */ if (seq != 0) seq++; /* * The information about the last finalized @seq might be inaccurate. * Search forward to find the current one. */ while (_prb_read_valid(rb, &seq, NULL, NULL)) seq++; return seq; } /** * prb_init() - Initialize a ringbuffer to use provided external buffers. * * @rb: The ringbuffer to initialize. * @text_buf: The data buffer for text data. * @textbits: The size of @text_buf as a power-of-2 value. * @descs: The descriptor buffer for ringbuffer records. * @descbits: The count of @descs items as a power-of-2 value. * @infos: The printk_info buffer for ringbuffer records. * * This is the public function available to writers to setup a ringbuffer * during runtime using provided buffers. * * This must match the initialization of DEFINE_PRINTKRB(). * * Context: Any context. */ void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int textbits, struct prb_desc *descs, unsigned int descbits, struct printk_info *infos) { memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0])); memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0])); rb->desc_ring.count_bits = descbits; rb->desc_ring.descs = descs; rb->desc_ring.infos = infos; atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.last_finalized_seq, 0); rb->text_data_ring.size_bits = textbits; rb->text_data_ring.data = text_buf; atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->fail, 0); atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits)); descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS; descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS; infos[0].seq = -(u64)_DESCS_COUNT(descbits); infos[_DESCS_COUNT(descbits) - 1].seq = 0; } /** * prb_record_text_space() - Query the full actual used ringbuffer space for * the text data of a reserved entry. * * @e: The successfully reserved entry to query. * * This is the public function available to writers to see how much actual * space is used in the ringbuffer to store the text data of the specified * entry. * * This function is only valid if @e has been successfully reserved using * prb_reserve(). * * Context: Any context. * Return: The size in bytes used by the text data of the associated record. */ unsigned int prb_record_text_space(struct prb_reserved_entry *e) { return e->text_space; } |
| 15 15 9 9 3 3 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 * Phillip Lougher <phillip@squashfs.org.uk> * * zlib_wrapper.c */ #include <linux/mutex.h> #include <linux/bio.h> #include <linux/slab.h> #include <linux/zlib.h> #include <linux/vmalloc.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" #include "page_actor.h" static void *zlib_init(struct squashfs_sb_info *dummy, void *buff) { z_stream *stream = kmalloc(sizeof(z_stream), GFP_KERNEL); if (stream == NULL) goto failed; stream->workspace = vmalloc(zlib_inflate_workspacesize()); if (stream->workspace == NULL) goto failed; return stream; failed: ERROR("Failed to allocate zlib workspace\n"); kfree(stream); return ERR_PTR(-ENOMEM); } static void zlib_free(void *strm) { z_stream *stream = strm; if (stream) vfree(stream->workspace); kfree(stream); } static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, struct bio *bio, int offset, int length, struct squashfs_page_actor *output) { struct bvec_iter_all iter_all = {}; struct bio_vec *bvec = bvec_init_iter_all(&iter_all); int zlib_init = 0, error = 0; z_stream *stream = strm; stream->avail_out = PAGE_SIZE; stream->next_out = squashfs_first_page(output); stream->avail_in = 0; if (IS_ERR(stream->next_out)) { error = PTR_ERR(stream->next_out); goto finish; } for (;;) { int zlib_err; if (stream->avail_in == 0) { const void *data; int avail; if (!bio_next_segment(bio, &iter_all)) { /* Z_STREAM_END must be reached. */ error = -EIO; break; } avail = min(length, ((int)bvec->bv_len) - offset); data = bvec_virt(bvec); length -= avail; stream->next_in = data + offset; stream->avail_in = avail; offset = 0; } if (stream->avail_out == 0) { stream->next_out = squashfs_next_page(output); if (IS_ERR(stream->next_out)) { error = PTR_ERR(stream->next_out); break; } else if (stream->next_out != NULL) stream->avail_out = PAGE_SIZE; } if (!zlib_init) { zlib_err = zlib_inflateInit(stream); if (zlib_err != Z_OK) { error = -EIO; break; } zlib_init = 1; } zlib_err = zlib_inflate(stream, Z_SYNC_FLUSH); if (zlib_err == Z_STREAM_END) break; if (zlib_err != Z_OK) { error = -EIO; break; } } finish: squashfs_finish_page(output); if (!error) if (zlib_inflateEnd(stream) != Z_OK) error = -EIO; return error ? error : stream->total_out; } const struct squashfs_decompressor squashfs_zlib_comp_ops = { .init = zlib_init, .free = zlib_free, .decompress = zlib_uncompress, .id = ZLIB_COMPRESSION, .name = "zlib", .alloc_buffer = 1, .supported = 1 }; |
| 8992 2774 2860 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H #define HAVE_JUMP_LABEL_BATCH #include <asm/asm.h> #include <asm/nops.h> #ifndef __ASSEMBLY__ #include <linux/stringify.h> #include <linux/types.h> #define JUMP_TABLE_ENTRY \ ".pushsection __jump_table, \"aw\" \n\t" \ _ASM_ALIGN "\n\t" \ ".long 1b - . \n\t" \ ".long %l[l_yes] - . \n\t" \ _ASM_PTR "%c0 + %c1 - .\n\t" \ ".popsection \n\t" #ifdef CONFIG_HAVE_JUMP_LABEL_HACK static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm goto("1:" "jmp %l[l_yes] # objtool NOPs this \n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (2 | branch) : : l_yes); return false; l_yes: return true; } #else /* !CONFIG_HAVE_JUMP_LABEL_HACK */ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { asm goto("1:" ".byte " __stringify(BYTES_NOP5) "\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } #endif /* CONFIG_HAVE_JUMP_LABEL_HACK */ static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { asm goto("1:" "jmp %l[l_yes]\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } extern int arch_jump_entry_size(struct jump_entry *entry); #endif /* __ASSEMBLY__ */ #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Forwarding Information Base. * * Authors: A.N.Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #ifndef _NET_IP_FIB_H #define _NET_IP_FIB_H #include <net/flow.h> #include <linux/seq_file.h> #include <linux/rcupdate.h> #include <net/fib_notifier.h> #include <net/fib_rules.h> #include <net/inet_dscp.h> #include <net/inetpeer.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/refcount.h> struct fib_config { u8 fc_dst_len; dscp_t fc_dscp; u8 fc_protocol; u8 fc_scope; u8 fc_type; u8 fc_gw_family; /* 2 bytes unused */ u32 fc_table; __be32 fc_dst; union { __be32 fc_gw4; struct in6_addr fc_gw6; }; int fc_oif; u32 fc_flags; u32 fc_priority; __be32 fc_prefsrc; u32 fc_nh_id; struct nlattr *fc_mx; struct rtnexthop *fc_mp; int fc_mx_len; int fc_mp_len; u32 fc_flow; u32 fc_nlflags; struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; }; struct fib_info; struct rtable; struct fib_nh_exception { struct fib_nh_exception __rcu *fnhe_next; int fnhe_genid; __be32 fnhe_daddr; u32 fnhe_pmtu; bool fnhe_mtu_locked; __be32 fnhe_gw; unsigned long fnhe_expires; struct rtable __rcu *fnhe_rth_input; struct rtable __rcu *fnhe_rth_output; unsigned long fnhe_stamp; struct rcu_head rcu; }; struct fnhe_hash_bucket { struct fib_nh_exception __rcu *chain; }; #define FNHE_HASH_SHIFT 11 #define FNHE_HASH_SIZE (1 << FNHE_HASH_SHIFT) #define FNHE_RECLAIM_DEPTH 5 struct fib_nh_common { struct net_device *nhc_dev; netdevice_tracker nhc_dev_tracker; int nhc_oif; unsigned char nhc_scope; u8 nhc_family; u8 nhc_gw_family; unsigned char nhc_flags; struct lwtunnel_state *nhc_lwtstate; union { __be32 ipv4; struct in6_addr ipv6; } nhc_gw; int nhc_weight; atomic_t nhc_upper_bound; /* v4 specific, but allows fib6_nh with v4 routes */ struct rtable __rcu * __percpu *nhc_pcpu_rth_output; struct rtable __rcu *nhc_rth_input; struct fnhe_hash_bucket __rcu *nhc_exceptions; }; struct fib_nh { struct fib_nh_common nh_common; struct hlist_node nh_hash; struct fib_info *nh_parent; #ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif __be32 nh_saddr; int nh_saddr_genid; #define fib_nh_family nh_common.nhc_family #define fib_nh_dev nh_common.nhc_dev #define fib_nh_dev_tracker nh_common.nhc_dev_tracker #define fib_nh_oif nh_common.nhc_oif #define fib_nh_flags nh_common.nhc_flags #define fib_nh_lws nh_common.nhc_lwtstate #define fib_nh_scope nh_common.nhc_scope #define fib_nh_gw_family nh_common.nhc_gw_family #define fib_nh_gw4 nh_common.nhc_gw.ipv4 #define fib_nh_gw6 nh_common.nhc_gw.ipv6 #define fib_nh_weight nh_common.nhc_weight #define fib_nh_upper_bound nh_common.nhc_upper_bound }; /* * This structure contains data shared by many of routes. */ struct nexthop; struct fib_info { struct hlist_node fib_hash; struct hlist_node fib_lhash; struct list_head nh_list; struct net *fib_net; refcount_t fib_treeref; refcount_t fib_clntref; unsigned int fib_flags; unsigned char fib_dead; unsigned char fib_protocol; unsigned char fib_scope; unsigned char fib_type; __be32 fib_prefsrc; u32 fib_tb_id; u32 fib_priority; struct dst_metrics *fib_metrics; #define fib_mtu fib_metrics->metrics[RTAX_MTU-1] #define fib_window fib_metrics->metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics->metrics[RTAX_RTT-1] #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; bool fib_nh_is_v6; bool nh_updated; bool pfsrc_removed; struct nexthop *nh; struct rcu_head rcu; struct fib_nh fib_nh[] __counted_by(fib_nhs); }; #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule; #endif struct fib_table; struct fib_result { __be32 prefix; unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; u32 tclassid; dscp_t dscp; struct fib_nh_common *nhc; struct fib_info *fi; struct fib_table *table; struct hlist_head *fa_head; }; struct fib_result_nl { __be32 fl_addr; /* To be looked up*/ u32 fl_mark; unsigned char fl_tos; unsigned char fl_scope; unsigned char tb_id_in; unsigned char tb_id; /* Results */ unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; int err; }; #ifdef CONFIG_IP_MULTIPLE_TABLES #define FIB_TABLE_HASHSZ 256 #else #define FIB_TABLE_HASHSZ 2 #endif __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope); __be32 fib_result_prefsrc(struct net *net, struct fib_result *res); #define FIB_RES_NHC(res) ((res).nhc) #define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev) #define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif) struct fib_rt_info { struct fib_info *fi; u32 tb_id; __be32 dst; int dst_len; dscp_t dscp; u8 type; u8 offload:1, trap:1, offload_failed:1, unused:5; }; struct fib_entry_notifier_info { struct fib_notifier_info info; /* must be first */ u32 dst; int dst_len; struct fib_info *fi; dscp_t dscp; u8 type; u32 tb_id; }; struct fib_nh_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib_nh *fib_nh; }; int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); void fib_info_notify_update(struct net *net, struct nl_info *info); int fib_notify(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); struct fib_table { struct hlist_node tb_hlist; u32 tb_id; int tb_num_default; struct rcu_head rcu; unsigned long *tb_data; unsigned long __data[]; }; struct fib_dump_filter { u32 table_id; /* filter_set is an optimization that an entry is set */ bool filter_set; bool dump_routes; bool dump_exceptions; bool rtnl_held; unsigned char protocol; unsigned char rt_type; unsigned int flags; struct net_device *dev; }; int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter); int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); #ifndef CONFIG_IP_MULTIPLE_TABLES #define TABLE_LOCAL_INDEX (RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1)) #define TABLE_MAIN_INDEX (RT_TABLE_MAIN & (FIB_TABLE_HASHSZ - 1)) static inline struct fib_table *fib_get_table(struct net *net, u32 id) { struct hlist_node *tb_hlist; struct hlist_head *ptr; ptr = id == RT_TABLE_LOCAL ? &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] : &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]; tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr)); return hlist_entry(tb_hlist, struct fib_table, tb_hlist); } static inline struct fib_table *fib_new_table(struct net *net, u32 id) { return fib_get_table(net, id); } static inline int fib_lookup(struct net *net, const struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; rcu_read_lock(); tb = fib_get_table(net, RT_TABLE_MAIN); if (tb) err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF); if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_has_custom_rules(const struct net *net) { return false; } static inline bool fib4_rule_default(const struct fib_rule *rule) { return true; } static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static inline unsigned int fib4_rules_seq_read(struct net *net) { return 0; } static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { return false; } #else /* CONFIG_IP_MULTIPLE_TABLES */ int __net_init fib4_rules_init(struct net *net); void __net_exit fib4_rules_exit(struct net *net); struct fib_table *fib_new_table(struct net *net, u32 id); struct fib_table *fib_get_table(struct net *net, u32 id); int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags); static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; flags |= FIB_LOOKUP_NOREF; if (net->ipv4.fib_has_custom_rules) return __fib_lookup(net, flp, res, flags); rcu_read_lock(); res->tclassid = 0; tb = rcu_dereference_rtnl(net->ipv4.fib_main); if (tb) err = fib_table_lookup(tb, flp, res, flags); if (!err) goto out; tb = rcu_dereference_rtnl(net->ipv4.fib_default); if (tb) err = fib_table_lookup(tb, flp, res, flags); out: if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_has_custom_rules(const struct net *net) { return net->ipv4.fib_has_custom_rules; } bool fib4_rule_default(const struct fib_rule *rule); int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); unsigned int fib4_rules_seq_read(struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; if (!net->ipv4.fib_rules_require_fldissect) return false; memset(flkeys, 0, sizeof(*flkeys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, flkeys, NULL, 0, 0, 0, flag); fl4->fl4_sport = flkeys->ports.src; fl4->fl4_dport = flkeys->ports.dst; fl4->flowi4_proto = flkeys->basic.ip_proto; return true; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack); __be32 fib_compute_spec_dst(struct sk_buff *skb); bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); 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); #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { return atomic_read(&net->ipv4.fib_num_tclassid_users); } #else static inline int fib_num_tclassid_users(struct net *net) { return 0; } #endif int fib_unmerge(struct net *net); static inline bool nhc_l3mdev_matches_dev(const struct fib_nh_common *nhc, const struct net_device *dev) { if (nhc->nhc_dev == dev || l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) return true; return false; } /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); /* Fields used for sysctl_fib_multipath_hash_fields. * Common to IPv4 and IPv6. * * Add new fields at the end. This is user API. */ #define FIB_MULTIPATH_HASH_FIELD_SRC_IP BIT(0) #define FIB_MULTIPATH_HASH_FIELD_DST_IP BIT(1) #define FIB_MULTIPATH_HASH_FIELD_IP_PROTO BIT(2) #define FIB_MULTIPATH_HASH_FIELD_FLOWLABEL BIT(3) #define FIB_MULTIPATH_HASH_FIELD_SRC_PORT BIT(4) #define FIB_MULTIPATH_HASH_FIELD_DST_PORT BIT(5) #define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP BIT(6) #define FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP BIT(7) #define FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO BIT(8) #define FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL BIT(9) #define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT BIT(10) #define FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT BIT(11) #define FIB_MULTIPATH_HASH_FIELD_OUTER_MASK \ (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_IP_PROTO | \ FIB_MULTIPATH_HASH_FIELD_FLOWLABEL | \ FIB_MULTIPATH_HASH_FIELD_SRC_PORT | \ FIB_MULTIPATH_HASH_FIELD_DST_PORT) #define FIB_MULTIPATH_HASH_FIELD_INNER_MASK \ (FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO | \ FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL | \ FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT | \ FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) #define FIB_MULTIPATH_HASH_FIELD_ALL_MASK \ (FIB_MULTIPATH_HASH_FIELD_OUTER_MASK | \ FIB_MULTIPATH_HASH_FIELD_INNER_MASK) #define FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK \ (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ FIB_MULTIPATH_HASH_FIELD_DST_IP | \ FIB_MULTIPATH_HASH_FIELD_IP_PROTO) #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); static void fib_multipath_hash_construct_key(siphash_key_t *key, u32 mp_seed) { u64 mp_seed_64 = mp_seed; key->key[0] = (mp_seed_64 << 32) | mp_seed_64; key->key[1] = key->key[0]; } static inline u32 fib_multipath_hash_from_keys(const struct net *net, struct flow_keys *keys) { siphash_aligned_key_t hash_key; u32 mp_seed; mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; fib_multipath_hash_construct_key(&hash_key, mp_seed); return flow_hash_from_keys_seed(keys, &hash_key); } #else static inline u32 fib_multipath_hash_from_keys(const struct net *net, struct flow_keys *keys) { return flow_hash_from_keys(keys); } #endif int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, struct netlink_ext_ack *extack); void fib_select_multipath(struct fib_result *res, int hash); void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb); int fib_nh_init(struct net *net, struct fib_nh *fib_nh, struct fib_config *cfg, int nh_weight, struct netlink_ext_ack *extack); void fib_nh_release(struct net *net, struct fib_nh *fib_nh); int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc, struct nlattr *fc_encap, u16 fc_encap_type, void *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib_nh_common_release(struct fib_nh_common *nhc); /* Exported by fib_trie.c */ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri); void fib_trie_init(void); struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, const struct flowi4 *flp); static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { #ifdef CONFIG_IP_ROUTE_CLASSID struct fib_nh_common *nhc = res->nhc; #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); *itag = nh->nh_tclassid << 16; } else { *itag = 0; } #ifdef CONFIG_IP_MULTIPLE_TABLES rtag = res->tclassid; if (*itag == 0) *itag = (rtag<<16); *itag |= (rtag>>16); #endif #endif } void fib_flush(struct net *net); void free_fib_info(struct fib_info *fi); static inline void fib_info_hold(struct fib_info *fi) { refcount_inc(&fi->fib_clntref); } static inline void fib_info_put(struct fib_info *fi) { if (refcount_dec_and_test(&fi->fib_clntref)) free_fib_info(fi); } #ifdef CONFIG_PROC_FS int __net_init fib_proc_init(struct net *net); void __net_exit fib_proc_exit(struct net *net); #else static inline int fib_proc_init(struct net *net) { return 0; } static inline void fib_proc_exit(struct net *net) { } #endif u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr); int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb); int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, u8 rt_family, unsigned char *flags, bool skip_oif); int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, int nh_weight, u8 rt_family, u32 nh_tclassid); #endif /* _NET_FIB_H */ |
| 33 201 2 199 2 199 117 117 16 179 126 77 8 211 211 58 203 62 151 60 142 199 2 197 199 59 142 80 60 23 80 198 198 28 28 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 | // SPDX-License-Identifier: GPL-2.0 #include "messages.h" #include "ctree.h" #include "delalloc-space.h" #include "block-rsv.h" #include "btrfs_inode.h" #include "space-info.h" #include "qgroup.h" #include "fs.h" /* * HOW DOES THIS WORK * * There are two stages to data reservations, one for data and one for metadata * to handle the new extents and checksums generated by writing data. * * * DATA RESERVATION * The general flow of the data reservation is as follows * * -> Reserve * We call into btrfs_reserve_data_bytes() for the user request bytes that * they wish to write. We make this reservation and add it to * space_info->bytes_may_use. We set EXTENT_DELALLOC on the inode io_tree * for the range and carry on if this is buffered, or follow up trying to * make a real allocation if we are pre-allocating or doing O_DIRECT. * * -> Use * At writepages()/prealloc/O_DIRECT time we will call into * btrfs_reserve_extent() for some part or all of this range of bytes. We * will make the allocation and subtract space_info->bytes_may_use by the * original requested length and increase the space_info->bytes_reserved by * the allocated length. This distinction is important because compression * may allocate a smaller on disk extent than we previously reserved. * * -> Allocation * finish_ordered_io() will insert the new file extent item for this range, * and then add a delayed ref update for the extent tree. Once that delayed * ref is written the extent size is subtracted from * space_info->bytes_reserved and added to space_info->bytes_used. * * Error handling * * -> By the reservation maker * This is the simplest case, we haven't completed our operation and we know * how much we reserved, we can simply call * btrfs_free_reserved_data_space*() and it will be removed from * space_info->bytes_may_use. * * -> After the reservation has been made, but before cow_file_range() * This is specifically for the delalloc case. You must clear * EXTENT_DELALLOC with the EXTENT_CLEAR_DATA_RESV bit, and the range will * be subtracted from space_info->bytes_may_use. * * METADATA RESERVATION * The general metadata reservation lifetimes are discussed elsewhere, this * will just focus on how it is used for delalloc space. * * We keep track of two things on a per inode bases * * ->outstanding_extents * This is the number of file extent items we'll need to handle all of the * outstanding DELALLOC space we have in this inode. We limit the maximum * size of an extent, so a large contiguous dirty area may require more than * one outstanding_extent, which is why count_max_extents() is used to * determine how many outstanding_extents get added. * * ->csum_bytes * This is essentially how many dirty bytes we have for this inode, so we * can calculate the number of checksum items we would have to add in order * to checksum our outstanding data. * * We keep a per-inode block_rsv in order to make it easier to keep track of * our reservation. We use btrfs_calculate_inode_block_rsv_size() to * calculate the current theoretical maximum reservation we would need for the * metadata for this inode. We call this and then adjust our reservation as * necessary, either by attempting to reserve more space, or freeing up excess * space. * * OUTSTANDING_EXTENTS HANDLING * * ->outstanding_extents is used for keeping track of how many extents we will * need to use for this inode, and it will fluctuate depending on where you are * in the life cycle of the dirty data. Consider the following normal case for * a completely clean inode, with a num_bytes < our maximum allowed extent size * * -> reserve * ->outstanding_extents += 1 (current value is 1) * * -> set_delalloc * ->outstanding_extents += 1 (current value is 2) * * -> btrfs_delalloc_release_extents() * ->outstanding_extents -= 1 (current value is 1) * * We must call this once we are done, as we hold our reservation for the * duration of our operation, and then assume set_delalloc will update the * counter appropriately. * * -> add ordered extent * ->outstanding_extents += 1 (current value is 2) * * -> btrfs_clear_delalloc_extent * ->outstanding_extents -= 1 (current value is 1) * * -> finish_ordered_io/btrfs_remove_ordered_extent * ->outstanding_extents -= 1 (current value is 0) * * Each stage is responsible for their own accounting of the extent, thus * making error handling and cleanup easier. */ int btrfs_alloc_data_chunk_ondemand(const struct btrfs_inode *inode, u64 bytes) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_DATA; /* Make sure bytes are sectorsize aligned */ bytes = ALIGN(bytes, fs_info->sectorsize); if (btrfs_is_free_space_inode(inode)) flush = BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE; return btrfs_reserve_data_bytes(fs_info, bytes, flush); } int btrfs_check_data_free_space(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len, bool noflush) { struct btrfs_fs_info *fs_info = inode->root->fs_info; enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_DATA; int ret; /* align the range */ len = round_up(start + len, fs_info->sectorsize) - round_down(start, fs_info->sectorsize); start = round_down(start, fs_info->sectorsize); if (noflush) flush = BTRFS_RESERVE_NO_FLUSH; else if (btrfs_is_free_space_inode(inode)) flush = BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE; ret = btrfs_reserve_data_bytes(fs_info, len, flush); if (ret < 0) return ret; /* Use new btrfs_qgroup_reserve_data to reserve precious data space. */ ret = btrfs_qgroup_reserve_data(inode, reserved, start, len); if (ret < 0) { btrfs_free_reserved_data_space_noquota(fs_info, len); extent_changeset_free(*reserved); *reserved = NULL; } else { ret = 0; } return ret; } /* * Called if we need to clear a data reservation for this inode * Normally in a error case. * * This one will *NOT* use accurate qgroup reserved space API, just for case * which we can't sleep and is sure it won't affect qgroup reserved space. * Like clear_bit_hook(). */ void btrfs_free_reserved_data_space_noquota(struct btrfs_fs_info *fs_info, u64 len) { struct btrfs_space_info *data_sinfo; ASSERT(IS_ALIGNED(len, fs_info->sectorsize)); data_sinfo = fs_info->data_sinfo; btrfs_space_info_free_bytes_may_use(fs_info, data_sinfo, len); } /* * Called if we need to clear a data reservation for this inode * Normally in a error case. * * This one will handle the per-inode data rsv map for accurate reserved * space framework. */ void btrfs_free_reserved_data_space(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len) { struct btrfs_fs_info *fs_info = inode->root->fs_info; /* Make sure the range is aligned to sectorsize */ len = round_up(start + len, fs_info->sectorsize) - round_down(start, fs_info->sectorsize); start = round_down(start, fs_info->sectorsize); btrfs_free_reserved_data_space_noquota(fs_info, len); btrfs_qgroup_free_data(inode, reserved, start, len, NULL); } /* * Release any excessive reservations for an inode. * * @inode: the inode we need to release from * @qgroup_free: free or convert qgroup meta. Unlike normal operation, qgroup * meta reservation needs to know if we are freeing qgroup * reservation or just converting it into per-trans. Normally * @qgroup_free is true for error handling, and false for normal * release. * * This is the same as btrfs_block_rsv_release, except that it handles the * tracepoint for the reservation. */ static void btrfs_inode_rsv_release(struct btrfs_inode *inode, bool qgroup_free) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_block_rsv *block_rsv = &inode->block_rsv; u64 released = 0; u64 qgroup_to_release = 0; /* * Since we statically set the block_rsv->size we just want to say we * are releasing 0 bytes, and then we'll just get the reservation over * the size free'd. */ released = btrfs_block_rsv_release(fs_info, block_rsv, 0, &qgroup_to_release); if (released > 0) trace_btrfs_space_reservation(fs_info, "delalloc", btrfs_ino(inode), released, 0); if (qgroup_free) btrfs_qgroup_free_meta_prealloc(inode->root, qgroup_to_release); else btrfs_qgroup_convert_reserved_meta(inode->root, qgroup_to_release); } static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode) { struct btrfs_block_rsv *block_rsv = &inode->block_rsv; u64 reserve_size = 0; u64 qgroup_rsv_size = 0; unsigned outstanding_extents; lockdep_assert_held(&inode->lock); outstanding_extents = inode->outstanding_extents; /* * Insert size for the number of outstanding extents, 1 normal size for * updating the inode. */ if (outstanding_extents) { reserve_size = btrfs_calc_insert_metadata_size(fs_info, outstanding_extents); reserve_size += btrfs_calc_metadata_size(fs_info, 1); } if (!(inode->flags & BTRFS_INODE_NODATASUM)) { u64 csum_leaves; csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes); reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves); } /* * For qgroup rsv, the calculation is very simple: * account one nodesize for each outstanding extent * * This is overestimating in most cases. */ qgroup_rsv_size = (u64)outstanding_extents * fs_info->nodesize; spin_lock(&block_rsv->lock); block_rsv->size = reserve_size; block_rsv->qgroup_rsv_size = qgroup_rsv_size; spin_unlock(&block_rsv->lock); } static void calc_inode_reservations(struct btrfs_inode *inode, u64 num_bytes, u64 disk_num_bytes, u64 *meta_reserve, u64 *qgroup_reserve) { struct btrfs_fs_info *fs_info = inode->root->fs_info; u64 nr_extents = count_max_extents(fs_info, num_bytes); u64 csum_leaves; u64 inode_update = btrfs_calc_metadata_size(fs_info, 1); if (inode->flags & BTRFS_INODE_NODATASUM) csum_leaves = 0; else csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); *meta_reserve = btrfs_calc_insert_metadata_size(fs_info, nr_extents + csum_leaves); /* * finish_ordered_io has to update the inode, so add the space required * for an inode update. */ *meta_reserve += inode_update; *qgroup_reserve = nr_extents * fs_info->nodesize; } int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, u64 disk_num_bytes, bool noflush) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *block_rsv = &inode->block_rsv; u64 meta_reserve, qgroup_reserve; unsigned nr_extents; enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL; int ret = 0; /* * If we are a free space inode we need to not flush since we will be in * the middle of a transaction commit. We also don't need the delalloc * mutex since we won't race with anybody. We need this mostly to make * lockdep shut its filthy mouth. * * If we have a transaction open (can happen if we call truncate_block * from truncate), then we need FLUSH_LIMIT so we don't deadlock. */ if (noflush || btrfs_is_free_space_inode(inode)) { flush = BTRFS_RESERVE_NO_FLUSH; } else { if (current->journal_info) flush = BTRFS_RESERVE_FLUSH_LIMIT; } num_bytes = ALIGN(num_bytes, fs_info->sectorsize); disk_num_bytes = ALIGN(disk_num_bytes, fs_info->sectorsize); /* * We always want to do it this way, every other way is wrong and ends * in tears. Pre-reserving the amount we are going to add will always * be the right way, because otherwise if we have enough parallelism we * could end up with thousands of inodes all holding little bits of * reservations they were able to make previously and the only way to * reclaim that space is to ENOSPC out the operations and clear * everything out and try again, which is bad. This way we just * over-reserve slightly, and clean up the mess when we are done. */ calc_inode_reservations(inode, num_bytes, disk_num_bytes, &meta_reserve, &qgroup_reserve); ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true, noflush); if (ret) return ret; ret = btrfs_reserve_metadata_bytes(fs_info, block_rsv->space_info, meta_reserve, flush); if (ret) { btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve); return ret; } /* * Now we need to update our outstanding extents and csum bytes _first_ * and then add the reservation to the block_rsv. This keeps us from * racing with an ordered completion or some such that would think it * needs to free the reservation we just made. */ nr_extents = count_max_extents(fs_info, num_bytes); spin_lock(&inode->lock); btrfs_mod_outstanding_extents(inode, nr_extents); if (!(inode->flags & BTRFS_INODE_NODATASUM)) inode->csum_bytes += disk_num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); /* Now we can safely add our space to our block rsv */ btrfs_block_rsv_add_bytes(block_rsv, meta_reserve, false); trace_btrfs_space_reservation(root->fs_info, "delalloc", btrfs_ino(inode), meta_reserve, 1); spin_lock(&block_rsv->lock); block_rsv->qgroup_rsv_reserved += qgroup_reserve; spin_unlock(&block_rsv->lock); return 0; } /* * Release a metadata reservation for an inode. * * @inode: the inode to release the reservation for. * @num_bytes: the number of bytes we are releasing. * @qgroup_free: free qgroup reservation or convert it to per-trans reservation * * This will release the metadata reservation for an inode. This can be called * once we complete IO for a given set of bytes to release their metadata * reservations, or on error for the same reason. */ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, bool qgroup_free) { struct btrfs_fs_info *fs_info = inode->root->fs_info; num_bytes = ALIGN(num_bytes, fs_info->sectorsize); spin_lock(&inode->lock); if (!(inode->flags & BTRFS_INODE_NODATASUM)) inode->csum_bytes -= num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); if (btrfs_is_testing(fs_info)) return; btrfs_inode_rsv_release(inode, qgroup_free); } /* * Release our outstanding_extents for an inode. * * @inode: the inode to balance the reservation for. * @num_bytes: the number of bytes we originally reserved with * * When we reserve space we increase outstanding_extents for the extents we may * add. Once we've set the range as delalloc or created our ordered extents we * have outstanding_extents to track the real usage, so we use this to free our * temporarily tracked outstanding_extents. This _must_ be used in conjunction * with btrfs_delalloc_reserve_metadata. */ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes) { struct btrfs_fs_info *fs_info = inode->root->fs_info; unsigned num_extents; spin_lock(&inode->lock); num_extents = count_max_extents(fs_info, num_bytes); btrfs_mod_outstanding_extents(inode, -num_extents); btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); if (btrfs_is_testing(fs_info)) return; btrfs_inode_rsv_release(inode, true); } /* * Reserve data and metadata space for delalloc * * @inode: inode we're writing to * @start: start range we are writing to * @len: how long the range we are writing to * @reserved: mandatory parameter, record actually reserved qgroup ranges of * current reservation. * * This will do the following things * * - reserve space in data space info for num bytes and reserve precious * corresponding qgroup space * (Done in check_data_free_space) * * - reserve space for metadata space, based on the number of outstanding * extents and how much csums will be needed also reserve metadata space in a * per root over-reserve method. * - add to the inodes->delalloc_bytes * - add it to the fs_info's delalloc inodes list. * (Above 3 all done in delalloc_reserve_metadata) * * Return 0 for success * Return <0 for error(-ENOSPC or -EDQUOT) */ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len) { int ret; ret = btrfs_check_data_free_space(inode, reserved, start, len, false); if (ret < 0) return ret; ret = btrfs_delalloc_reserve_metadata(inode, len, len, false); if (ret < 0) { btrfs_free_reserved_data_space(inode, *reserved, start, len); extent_changeset_free(*reserved); *reserved = NULL; } return ret; } /* * Release data and metadata space for delalloc * * @inode: inode we're releasing space for * @reserved: list of changed/reserved ranges * @start: start position of the space already reserved * @len: length of the space already reserved * @qgroup_free: should qgroup reserved-space also be freed * * Release the metadata space that was not used and will decrement * ->delalloc_bytes and remove it from the fs_info->delalloc_inodes list if * there are no delalloc bytes left. Also it will handle the qgroup reserved * space. */ void btrfs_delalloc_release_space(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, bool qgroup_free) { btrfs_delalloc_release_metadata(inode, len, qgroup_free); btrfs_free_reserved_data_space(inode, reserved, start, len); } |
| 41 41 30 26 28 27 8 8 25 25 11 11 19 19 19 18 19 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 | /* SPDX-License-Identifier: LGPL-2.1+ */ /* Copyright (C) 2022 Kent Overstreet */ #ifndef _BCACHEFS_PRINTBUF_H #define _BCACHEFS_PRINTBUF_H /* * Printbufs: Simple strings for printing to, with optional heap allocation * * This code has provisions for use in userspace, to aid in making other code * portable between kernelspace and userspace. * * Basic example: * struct printbuf buf = PRINTBUF; * * prt_printf(&buf, "foo="); * foo_to_text(&buf, foo); * printk("%s", buf.buf); * printbuf_exit(&buf); * * Or * struct printbuf buf = PRINTBUF_EXTERN(char_buf, char_buf_size) * * We can now write pretty printers instead of writing code that dumps * everything to the kernel log buffer, and then those pretty-printers can be * used by other code that outputs to kernel log, sysfs, debugfs, etc. * * Memory allocation: Outputing to a printbuf may allocate memory. This * allocation is done with GFP_KERNEL, by default: use the newer * memalloc_*_(save|restore) functions as needed. * * Since no equivalent yet exists for GFP_ATOMIC/GFP_NOWAIT, memory allocations * will be done with GFP_NOWAIT if printbuf->atomic is nonzero. * * It's allowed to grab the output buffer and free it later with kfree() instead * of using printbuf_exit(), if the user just needs a heap allocated string at * the end. * * Memory allocation failures: We don't return errors directly, because on * memory allocation failure we usually don't want to bail out and unwind - we * want to print what we've got, on a best-effort basis. But code that does want * to return -ENOMEM may check printbuf.allocation_failure. * * Indenting, tabstops: * * To aid is writing multi-line pretty printers spread across multiple * functions, printbufs track the current indent level. * * printbuf_indent_push() and printbuf_indent_pop() increase and decrease the current indent * level, respectively. * * To use tabstops, set printbuf->tabstops[]; they are in units of spaces, from * start of line. Once set, prt_tab() will output spaces up to the next tabstop. * prt_tab_rjust() will also advance the current line of text up to the next * tabstop, but it does so by shifting text since the previous tabstop up to the * next tabstop - right justifying it. * * Make sure you use prt_newline() instead of \n in the format string for indent * level and tabstops to work corretly. * * Output units: printbuf->units exists to tell pretty-printers how to output * numbers: a raw value (e.g. directly from a superblock field), as bytes, or as * human readable bytes. prt_units() obeys it. */ #include <linux/kernel.h> #include <linux/string.h> enum printbuf_si { PRINTBUF_UNITS_2, /* use binary powers of 2^10 */ PRINTBUF_UNITS_10, /* use powers of 10^3 (standard SI) */ }; #define PRINTBUF_INLINE_TABSTOPS 6 struct printbuf { char *buf; unsigned size; unsigned pos; unsigned last_newline; unsigned last_field; unsigned indent; /* * If nonzero, allocations will be done with GFP_ATOMIC: */ u8 atomic; bool allocation_failure:1; bool heap_allocated:1; bool overflow:1; enum printbuf_si si_units:1; bool human_readable_units:1; bool has_indent_or_tabstops:1; bool suppress_indent_tabstop_handling:1; u8 nr_tabstops; /* * Do not modify directly: use printbuf_tabstop_add(), * printbuf_tabstop_get() */ u8 cur_tabstop; u8 _tabstops[PRINTBUF_INLINE_TABSTOPS]; }; int bch2_printbuf_make_room(struct printbuf *, unsigned); __printf(2, 3) void bch2_prt_printf(struct printbuf *out, const char *fmt, ...); __printf(2, 0) void bch2_prt_vprintf(struct printbuf *out, const char *fmt, va_list); const char *bch2_printbuf_str(const struct printbuf *); void bch2_printbuf_exit(struct printbuf *); void bch2_printbuf_tabstops_reset(struct printbuf *); void bch2_printbuf_tabstop_pop(struct printbuf *); int bch2_printbuf_tabstop_push(struct printbuf *, unsigned); void bch2_printbuf_indent_add(struct printbuf *, unsigned); void bch2_printbuf_indent_sub(struct printbuf *, unsigned); void bch2_prt_newline(struct printbuf *); void bch2_printbuf_strip_trailing_newline(struct printbuf *); void bch2_prt_tab(struct printbuf *); void bch2_prt_tab_rjust(struct printbuf *); void bch2_prt_bytes_indented(struct printbuf *, const char *, unsigned); void bch2_prt_human_readable_u64(struct printbuf *, u64); void bch2_prt_human_readable_s64(struct printbuf *, s64); void bch2_prt_units_u64(struct printbuf *, u64); void bch2_prt_units_s64(struct printbuf *, s64); void bch2_prt_string_option(struct printbuf *, const char * const[], size_t); void bch2_prt_bitflags(struct printbuf *, const char * const[], u64); void bch2_prt_bitflags_vector(struct printbuf *, const char * const[], unsigned long *, unsigned); /* Initializer for a heap allocated printbuf: */ #define PRINTBUF ((struct printbuf) { .heap_allocated = true }) /* Initializer a printbuf that points to an external buffer: */ #define PRINTBUF_EXTERN(_buf, _size) \ ((struct printbuf) { \ .buf = _buf, \ .size = _size, \ }) /* * Returns size remaining of output buffer: */ static inline unsigned printbuf_remaining_size(struct printbuf *out) { if (WARN_ON(out->size && out->pos >= out->size)) out->pos = out->size - 1; return out->size - out->pos; } /* * Returns number of characters we can print to the output buffer - i.e. * excluding the terminating nul: */ static inline unsigned printbuf_remaining(struct printbuf *out) { return out->size ? printbuf_remaining_size(out) - 1 : 0; } static inline unsigned printbuf_written(struct printbuf *out) { return out->size ? min(out->pos, out->size - 1) : 0; } static inline void printbuf_nul_terminate_reserved(struct printbuf *out) { if (WARN_ON(out->size && out->pos >= out->size)) out->pos = out->size - 1; if (out->size) out->buf[out->pos] = 0; } static inline void printbuf_nul_terminate(struct printbuf *out) { bch2_printbuf_make_room(out, 1); printbuf_nul_terminate_reserved(out); } /* Doesn't call bch2_printbuf_make_room(), doesn't nul terminate: */ static inline void __prt_char_reserved(struct printbuf *out, char c) { if (printbuf_remaining(out)) out->buf[out->pos++] = c; } /* Doesn't nul terminate: */ static inline void __prt_char(struct printbuf *out, char c) { bch2_printbuf_make_room(out, 1); __prt_char_reserved(out, c); } static inline void prt_char(struct printbuf *out, char c) { bch2_printbuf_make_room(out, 2); __prt_char_reserved(out, c); printbuf_nul_terminate_reserved(out); } static inline void __prt_chars_reserved(struct printbuf *out, char c, unsigned n) { unsigned can_print = min(n, printbuf_remaining(out)); for (unsigned i = 0; i < can_print; i++) out->buf[out->pos++] = c; } static inline void prt_chars(struct printbuf *out, char c, unsigned n) { bch2_printbuf_make_room(out, n); __prt_chars_reserved(out, c, n); printbuf_nul_terminate_reserved(out); } static inline void prt_bytes(struct printbuf *out, const void *b, unsigned n) { bch2_printbuf_make_room(out, n); unsigned can_print = min(n, printbuf_remaining(out)); for (unsigned i = 0; i < can_print; i++) out->buf[out->pos++] = ((char *) b)[i]; printbuf_nul_terminate(out); } static inline void prt_str(struct printbuf *out, const char *str) { prt_bytes(out, str, strlen(str)); } static inline void prt_str_indented(struct printbuf *out, const char *str) { bch2_prt_bytes_indented(out, str, strlen(str)); } static inline void prt_hex_byte(struct printbuf *out, u8 byte) { bch2_printbuf_make_room(out, 3); __prt_char_reserved(out, hex_asc_hi(byte)); __prt_char_reserved(out, hex_asc_lo(byte)); printbuf_nul_terminate_reserved(out); } static inline void prt_hex_byte_upper(struct printbuf *out, u8 byte) { bch2_printbuf_make_room(out, 3); __prt_char_reserved(out, hex_asc_upper_hi(byte)); __prt_char_reserved(out, hex_asc_upper_lo(byte)); printbuf_nul_terminate_reserved(out); } /** * printbuf_reset - re-use a printbuf without freeing and re-initializing it: */ static inline void printbuf_reset(struct printbuf *buf) { buf->pos = 0; buf->allocation_failure = 0; buf->indent = 0; buf->nr_tabstops = 0; buf->cur_tabstop = 0; } /** * printbuf_atomic_inc - mark as entering an atomic section */ static inline void printbuf_atomic_inc(struct printbuf *buf) { buf->atomic++; } /** * printbuf_atomic_inc - mark as leaving an atomic section */ static inline void printbuf_atomic_dec(struct printbuf *buf) { buf->atomic--; } #endif /* _BCACHEFS_PRINTBUF_H */ |
| 1 2 246 325 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PID_H #define _LINUX_PID_H #include <linux/pid_types.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/sched.h> #include <linux/wait.h> /* * What is struct pid? * * A struct pid is the kernel's internal notion of a process identifier. * It refers to individual tasks, process groups, and sessions. While * there are processes attached to it the struct pid lives in a hash * table, so it and then the processes that it refers to can be found * quickly from the numeric pid value. The attached processes may be * quickly accessed by following pointers from struct pid. * * Storing pid_t values in the kernel and referring to them later has a * problem. The process originally with that pid may have exited and the * pid allocator wrapped, and another process could have come along * and been assigned that pid. * * Referring to user space processes by holding a reference to struct * task_struct has a problem. When the user space process exits * the now useless task_struct is still kept. A task_struct plus a * stack consumes around 10K of low kernel memory. More precisely * this is THREAD_SIZE + sizeof(struct task_struct). By comparison * a struct pid is about 64 bytes. * * Holding a reference to struct pid solves both of these problems. * It is small so holding a reference does not consume a lot of * resources, and since a new struct pid is allocated when the numeric pid * value is reused (when pids wrap around) we don't mistakenly refer to new * processes. */ /* * struct upid is used to get the id of the struct pid, as it is * seen in particular namespace. Later the struct pid is found with * find_pid_ns() using the int nr and struct pid_namespace *ns. */ #define RESERVED_PIDS 300 struct upid { int nr; struct pid_namespace *ns; }; struct pid { refcount_t count; unsigned int level; spinlock_t lock; struct dentry *stashed; u64 ino; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; /* wait queue for pidfd notifications */ wait_queue_head_t wait_pidfd; struct rcu_head rcu; struct upid numbers[]; }; extern struct pid init_struct_pid; struct file; struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); void do_notify_pidfd(struct task_struct *task); static inline struct pid *get_pid(struct pid *pid) { if (pid) refcount_inc(&pid->count); return pid; } extern void put_pid(struct pid *pid); extern struct task_struct *pid_task(struct pid *pid, enum pid_type); static inline bool pid_has_task(struct pid *pid, enum pid_type type) { return !hlist_empty(&pid->tasks[type]); } extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type); extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); /* * these helpers must be called with the tasklist_lock write-held. */ extern void attach_pid(struct task_struct *task, enum pid_type); extern void detach_pid(struct task_struct *task, enum pid_type); extern void change_pid(struct task_struct *task, enum pid_type, struct pid *pid); extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); extern int pid_max; extern int pid_max_min, pid_max_max; /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. * * find_pid_ns() finds the pid in the namespace specified * find_vpid() finds the pid by its virtual id, i.e. in the current namespace * * see also find_task_by_vpid() set in include/linux/sched.h */ extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns); extern struct pid *find_vpid(int nr); /* * Lookup a PID in the hash table, and return with it's count elevated. */ extern struct pid *find_get_pid(int nr); extern struct pid *find_ge_pid(int nr, struct pid_namespace *); extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size); extern void free_pid(struct pid *pid); extern void disable_pid_allocation(struct pid_namespace *ns); /* * ns_of_pid() returns the pid namespace in which the specified pid was * allocated. * * NOTE: * ns_of_pid() is expected to be called for a process (task) that has * an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid * is expected to be non-NULL. If @pid is NULL, caller should handle * the resulting NULL pid-ns. */ static inline struct pid_namespace *ns_of_pid(struct pid *pid) { struct pid_namespace *ns = NULL; if (pid) ns = pid->numbers[pid->level].ns; return ns; } /* * is_child_reaper returns true if the pid is the init process * of the current namespace. As this one could be checked before * pid_ns->child_reaper is assigned in copy_process, we check * with the pid number. */ static inline bool is_child_reaper(struct pid *pid) { return pid->numbers[pid->level].nr == 1; } /* * the helpers to get the pid's id seen from different namespaces * * pid_nr() : global id, i.e. the id seen from the init namespace; * pid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * pid_nr_ns() : id seen from the ns specified. * * see also task_xid_nr() etc in include/linux/sched.h */ static inline pid_t pid_nr(struct pid *pid) { pid_t nr = 0; if (pid) nr = pid->numbers[0].nr; return nr; } pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns); pid_t pid_vnr(struct pid *pid); #define do_each_pid_task(pid, type, task) \ do { \ if ((pid) != NULL) \ hlist_for_each_entry_rcu((task), \ &(pid)->tasks[type], pid_links[type]) { /* * Both old and new leaders may be attached to * the same pid in the middle of de_thread(). */ #define while_each_pid_task(pid, type, task) \ if (type == PIDTYPE_PID) \ break; \ } \ } while (0) #define do_each_pid_thread(pid, type, task) \ do_each_pid_task(pid, type, task) { \ struct task_struct *tg___ = task; \ for_each_thread(tg___, task) { #define while_each_pid_thread(pid, type, task) \ } \ task = tg___; \ } while_each_pid_task(pid, type, task) static inline struct pid *task_pid(struct task_struct *task) { return task->thread_pid; } /* * the helpers to get the task's different pids as they are seen * from various namespaces * * task_xid_nr() : global id, i.e. the id seen from the init namespace; * task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * task_xid_nr_ns() : id seen from the ns specified; * * see also pid_nr() etc in include/linux/pid.h */ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); static inline pid_t task_pid_nr(struct task_struct *tsk) { return tsk->pid; } static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); } static inline pid_t task_pid_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); } static inline pid_t task_tgid_nr(struct task_struct *tsk) { return tsk->tgid; } /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. * * Test if a process is not yet dead (at most zombie state) * If pid_alive fails, then pointers within the task structure * can be stale and must not be dereferenced. * * Return: 1 if the process is alive. 0 otherwise. */ static inline int pid_alive(const struct task_struct *p) { return p->thread_pid != NULL; } static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); } static inline pid_t task_pgrp_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); } static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); } static inline pid_t task_session_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); } static inline pid_t task_tgid_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); } static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) { pid_t pid = 0; rcu_read_lock(); if (pid_alive(tsk)) pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); rcu_read_unlock(); return pid; } static inline pid_t task_ppid_nr(const struct task_struct *tsk) { return task_ppid_nr_ns(tsk, &init_pid_ns); } /* Obsolete, do not use: */ static inline pid_t task_pgrp_nr(struct task_struct *tsk) { return task_pgrp_nr_ns(tsk, &init_pid_ns); } /** * is_global_init - check if a task structure is init. Since init * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. * * Return: 1 if the task structure is init. 0 otherwise. */ static inline int is_global_init(struct task_struct *tsk) { return task_tgid_nr(tsk) == 1; } #endif /* _LINUX_PID_H */ |
| 4 4 4 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | // SPDX-License-Identifier: GPL-2.0-or-later /* AFS cell alias detection * * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/slab.h> #include <linux/sched.h> #include <linux/namei.h> #include <keys/rxrpc-type.h> #include "internal.h" /* * Sample a volume. */ static struct afs_volume *afs_sample_volume(struct afs_cell *cell, struct key *key, const char *name, unsigned int namelen) { struct afs_volume *volume; struct afs_fs_context fc = { .type = 0, /* Explicitly leave it to the VLDB */ .volnamesz = namelen, .volname = name, .net = cell->net, .cell = cell, .key = key, /* This might need to be something */ }; volume = afs_create_volume(&fc); _leave(" = %p", volume); return volume; } /* * Compare the address lists of a pair of fileservers. */ static int afs_compare_fs_alists(const struct afs_server *server_a, const struct afs_server *server_b) { const struct afs_addr_list *la, *lb; int a = 0, b = 0, addr_matches = 0; la = rcu_dereference(server_a->endpoint_state)->addresses; lb = rcu_dereference(server_b->endpoint_state)->addresses; while (a < la->nr_addrs && b < lb->nr_addrs) { unsigned long pa = (unsigned long)la->addrs[a].peer; unsigned long pb = (unsigned long)lb->addrs[b].peer; long diff = pa - pb; if (diff < 0) { a++; } else if (diff > 0) { b++; } else { addr_matches++; a++; b++; } } return addr_matches; } /* * Compare the fileserver lists of two volumes. The server lists are sorted in * order of ascending UUID. */ static int afs_compare_volume_slists(const struct afs_volume *vol_a, const struct afs_volume *vol_b) { const struct afs_server_list *la, *lb; int i, a = 0, b = 0, uuid_matches = 0, addr_matches = 0; la = rcu_dereference(vol_a->servers); lb = rcu_dereference(vol_b->servers); for (i = 0; i < AFS_MAXTYPES; i++) if (vol_a->vids[i] != vol_b->vids[i]) return 0; while (a < la->nr_servers && b < lb->nr_servers) { const struct afs_server *server_a = la->servers[a].server; const struct afs_server *server_b = lb->servers[b].server; int diff = memcmp(&server_a->uuid, &server_b->uuid, sizeof(uuid_t)); if (diff < 0) { a++; } else if (diff > 0) { b++; } else { uuid_matches++; addr_matches += afs_compare_fs_alists(server_a, server_b); a++; b++; } } _leave(" = %d [um %d]", addr_matches, uuid_matches); return addr_matches; } /* * Compare root.cell volumes. */ static int afs_compare_cell_roots(struct afs_cell *cell) { struct afs_cell *p; _enter(""); rcu_read_lock(); hlist_for_each_entry_rcu(p, &cell->net->proc_cells, proc_link) { if (p == cell || p->alias_of) continue; if (!p->root_volume) continue; /* Ignore cells that don't have a root.cell volume. */ if (afs_compare_volume_slists(cell->root_volume, p->root_volume) != 0) goto is_alias; } rcu_read_unlock(); _leave(" = 0"); return 0; is_alias: rcu_read_unlock(); cell->alias_of = afs_use_cell(p, afs_cell_trace_use_alias); return 1; } /* * Query the new cell for a volume from a cell we're already using. */ static int afs_query_for_alias_one(struct afs_cell *cell, struct key *key, struct afs_cell *p) { struct afs_volume *volume, *pvol = NULL; int ret; /* Arbitrarily pick a volume from the list. */ read_seqlock_excl(&p->volume_lock); if (!RB_EMPTY_ROOT(&p->volumes)) pvol = afs_get_volume(rb_entry(p->volumes.rb_node, struct afs_volume, cell_node), afs_volume_trace_get_query_alias); read_sequnlock_excl(&p->volume_lock); if (!pvol) return 0; _enter("%s:%s", cell->name, pvol->name); /* And see if it's in the new cell. */ volume = afs_sample_volume(cell, key, pvol->name, pvol->name_len); if (IS_ERR(volume)) { afs_put_volume(pvol, afs_volume_trace_put_query_alias); if (PTR_ERR(volume) != -ENOMEDIUM) return PTR_ERR(volume); /* That volume is not in the new cell, so not an alias */ return 0; } /* The new cell has a like-named volume also - compare volume ID, * server and address lists. */ ret = 0; if (pvol->vid == volume->vid) { rcu_read_lock(); if (afs_compare_volume_slists(volume, pvol)) ret = 1; rcu_read_unlock(); } afs_put_volume(volume, afs_volume_trace_put_query_alias); afs_put_volume(pvol, afs_volume_trace_put_query_alias); return ret; } /* * Query the new cell for volumes we know exist in cells we're already using. */ static int afs_query_for_alias(struct afs_cell *cell, struct key *key) { struct afs_cell *p; _enter("%s", cell->name); if (mutex_lock_interruptible(&cell->net->proc_cells_lock) < 0) return -ERESTARTSYS; hlist_for_each_entry(p, &cell->net->proc_cells, proc_link) { if (p == cell || p->alias_of) continue; if (RB_EMPTY_ROOT(&p->volumes)) continue; if (p->root_volume) continue; /* Ignore cells that have a root.cell volume. */ afs_use_cell(p, afs_cell_trace_use_check_alias); mutex_unlock(&cell->net->proc_cells_lock); if (afs_query_for_alias_one(cell, key, p) != 0) goto is_alias; if (mutex_lock_interruptible(&cell->net->proc_cells_lock) < 0) { afs_unuse_cell(cell->net, p, afs_cell_trace_unuse_check_alias); return -ERESTARTSYS; } afs_unuse_cell(cell->net, p, afs_cell_trace_unuse_check_alias); } mutex_unlock(&cell->net->proc_cells_lock); _leave(" = 0"); return 0; is_alias: cell->alias_of = p; /* Transfer our ref */ return 1; } /* * Look up a VLDB record for a volume. */ static char *afs_vl_get_cell_name(struct afs_cell *cell, struct key *key) { struct afs_vl_cursor vc; char *cell_name = ERR_PTR(-EDESTADDRREQ); bool skipped = false, not_skipped = false; int ret; if (!afs_begin_vlserver_operation(&vc, cell, key)) return ERR_PTR(-ERESTARTSYS); while (afs_select_vlserver(&vc)) { if (!test_bit(AFS_VLSERVER_FL_IS_YFS, &vc.server->flags)) { vc.call_error = -EOPNOTSUPP; skipped = true; continue; } not_skipped = true; cell_name = afs_yfsvl_get_cell_name(&vc); } ret = afs_end_vlserver_operation(&vc); if (skipped && !not_skipped) ret = -EOPNOTSUPP; return ret < 0 ? ERR_PTR(ret) : cell_name; } static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) { struct afs_cell *master; char *cell_name; cell_name = afs_vl_get_cell_name(cell, key); if (IS_ERR(cell_name)) return PTR_ERR(cell_name); if (strcmp(cell_name, cell->name) == 0) { kfree(cell_name); return 0; } master = afs_lookup_cell(cell->net, cell_name, strlen(cell_name), NULL, false); kfree(cell_name); if (IS_ERR(master)) return PTR_ERR(master); cell->alias_of = master; /* Transfer our ref */ return 1; } static int afs_do_cell_detect_alias(struct afs_cell *cell, struct key *key) { struct afs_volume *root_volume; int ret; _enter("%s", cell->name); ret = yfs_check_canonical_cell_name(cell, key); if (ret != -EOPNOTSUPP) return ret; /* Try and get the root.cell volume for comparison with other cells */ root_volume = afs_sample_volume(cell, key, "root.cell", 9); if (!IS_ERR(root_volume)) { cell->root_volume = root_volume; return afs_compare_cell_roots(cell); } if (PTR_ERR(root_volume) != -ENOMEDIUM) return PTR_ERR(root_volume); /* Okay, this cell doesn't have an root.cell volume. We need to * locate some other random volume and use that to check. */ return afs_query_for_alias(cell, key); } /* * Check to see if a new cell is an alias of a cell we already have. At this * point we have the cell's volume server list. * * Returns 0 if we didn't detect an alias, 1 if we found an alias and an error * if we had problems gathering the data required. In the case the we did * detect an alias, cell->alias_of is set to point to the assumed master. */ int afs_cell_detect_alias(struct afs_cell *cell, struct key *key) { struct afs_net *net = cell->net; int ret; if (mutex_lock_interruptible(&net->cells_alias_lock) < 0) return -ERESTARTSYS; if (test_bit(AFS_CELL_FL_CHECK_ALIAS, &cell->flags)) { ret = afs_do_cell_detect_alias(cell, key); if (ret >= 0) clear_bit_unlock(AFS_CELL_FL_CHECK_ALIAS, &cell->flags); } else { ret = cell->alias_of ? 1 : 0; } mutex_unlock(&net->cells_alias_lock); if (ret == 1) pr_notice("kAFS: Cell %s is an alias of %s\n", cell->name, cell->alias_of->name); return ret; } |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xfrm_state.c * * Changes: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * IPv6 support * YOSHIFUJI Hideaki @USAGI * Split up af-specific functions * Derek Atkins <derek@ihtfp.com> * Add UDP Encapsulation * */ #include <linux/compat.h> #include <linux/workqueue.h> #include <net/xfrm.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/audit.h> #include <linux/uaccess.h> #include <linux/ktime.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <crypto/aead.h> #include "xfrm_hash.h" #define xfrm_state_deref_prot(table, net) \ rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) static void xfrm_state_gc_task(struct work_struct *work); /* Each xfrm_state may be linked to two tables: 1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl) 2. Hash table by (daddr,family,reqid) to find what SAs exist for given destination/tunnel endpoint. (output) */ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); static HLIST_HEAD(xfrm_state_gc_list); static HLIST_HEAD(xfrm_state_dev_gc_list); static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x) { return refcount_inc_not_zero(&x->refcnt); } static inline unsigned int xfrm_dst_hash(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u32 reqid, unsigned short family) { return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask); } static inline unsigned int xfrm_src_hash(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask); } static inline unsigned int xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask); } static unsigned int xfrm_seq_hash(struct net *net, u32 seq) { return __xfrm_seq_hash(seq, net->xfrm.state_hmask); } #define XFRM_STATE_INSERT(by, _n, _h, _type) \ { \ struct xfrm_state *_x = NULL; \ \ if (_type != XFRM_DEV_OFFLOAD_PACKET) { \ hlist_for_each_entry_rcu(_x, _h, by) { \ if (_x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \ continue; \ break; \ } \ } \ \ if (!_x || _x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \ /* SAD is empty or consist from HW SAs only */ \ hlist_add_head_rcu(_n, _h); \ else \ hlist_add_before_rcu(_n, &_x->by); \ } static void xfrm_hash_transfer(struct hlist_head *list, struct hlist_head *ndsttable, struct hlist_head *nsrctable, struct hlist_head *nspitable, struct hlist_head *nseqtable, unsigned int nhashmask) { struct hlist_node *tmp; struct xfrm_state *x; hlist_for_each_entry_safe(x, tmp, list, bydst) { unsigned int h; h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family, nhashmask); XFRM_STATE_INSERT(bydst, &x->bydst, ndsttable + h, x->xso.type); h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr, x->props.family, nhashmask); XFRM_STATE_INSERT(bysrc, &x->bysrc, nsrctable + h, x->xso.type); if (x->id.spi) { h = __xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, x->props.family, nhashmask); XFRM_STATE_INSERT(byspi, &x->byspi, nspitable + h, x->xso.type); } if (x->km.seq) { h = __xfrm_seq_hash(x->km.seq, nhashmask); XFRM_STATE_INSERT(byseq, &x->byseq, nseqtable + h, x->xso.type); } } } static unsigned long xfrm_hash_new_size(unsigned int state_hmask) { return ((state_hmask + 1) << 1) * sizeof(struct hlist_head); } static void xfrm_hash_resize(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.state_hash_work); struct hlist_head *ndst, *nsrc, *nspi, *nseq, *odst, *osrc, *ospi, *oseq; unsigned long nsize, osize; unsigned int nhashmask, ohashmask; int i; nsize = xfrm_hash_new_size(net->xfrm.state_hmask); ndst = xfrm_hash_alloc(nsize); if (!ndst) return; nsrc = xfrm_hash_alloc(nsize); if (!nsrc) { xfrm_hash_free(ndst, nsize); return; } nspi = xfrm_hash_alloc(nsize); if (!nspi) { xfrm_hash_free(ndst, nsize); xfrm_hash_free(nsrc, nsize); return; } nseq = xfrm_hash_alloc(nsize); if (!nseq) { xfrm_hash_free(ndst, nsize); xfrm_hash_free(nsrc, nsize); xfrm_hash_free(nspi, nsize); return; } spin_lock_bh(&net->xfrm.xfrm_state_lock); write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net); for (i = net->xfrm.state_hmask; i >= 0; i--) xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nseq, nhashmask); osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net); ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net); oseq = xfrm_state_deref_prot(net->xfrm.state_byseq, net); ohashmask = net->xfrm.state_hmask; rcu_assign_pointer(net->xfrm.state_bydst, ndst); rcu_assign_pointer(net->xfrm.state_bysrc, nsrc); rcu_assign_pointer(net->xfrm.state_byspi, nspi); rcu_assign_pointer(net->xfrm.state_byseq, nseq); net->xfrm.state_hmask = nhashmask; write_seqcount_end(&net->xfrm.xfrm_state_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_state_lock); osize = (ohashmask + 1) * sizeof(struct hlist_head); synchronize_rcu(); xfrm_hash_free(odst, osize); xfrm_hash_free(osrc, osize); xfrm_hash_free(ospi, osize); xfrm_hash_free(oseq, osize); } static DEFINE_SPINLOCK(xfrm_state_afinfo_lock); static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO]; static DEFINE_SPINLOCK(xfrm_state_gc_lock); static DEFINE_SPINLOCK(xfrm_state_dev_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); static bool km_is_alive(const struct km_event *c); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); int xfrm_register_type(const struct xfrm_type *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); int err = 0; if (!afinfo) return -EAFNOSUPPORT; #define X(afi, T, name) do { \ WARN_ON((afi)->type_ ## name); \ (afi)->type_ ## name = (T); \ } while (0) switch (type->proto) { case IPPROTO_COMP: X(afinfo, type, comp); break; case IPPROTO_AH: X(afinfo, type, ah); break; case IPPROTO_ESP: X(afinfo, type, esp); break; case IPPROTO_IPIP: X(afinfo, type, ipip); break; case IPPROTO_DSTOPTS: X(afinfo, type, dstopts); break; case IPPROTO_ROUTING: X(afinfo, type, routing); break; case IPPROTO_IPV6: X(afinfo, type, ipip6); break; default: WARN_ON(1); err = -EPROTONOSUPPORT; break; } #undef X rcu_read_unlock(); return err; } EXPORT_SYMBOL(xfrm_register_type); void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return; #define X(afi, T, name) do { \ WARN_ON((afi)->type_ ## name != (T)); \ (afi)->type_ ## name = NULL; \ } while (0) switch (type->proto) { case IPPROTO_COMP: X(afinfo, type, comp); break; case IPPROTO_AH: X(afinfo, type, ah); break; case IPPROTO_ESP: X(afinfo, type, esp); break; case IPPROTO_IPIP: X(afinfo, type, ipip); break; case IPPROTO_DSTOPTS: X(afinfo, type, dstopts); break; case IPPROTO_ROUTING: X(afinfo, type, routing); break; case IPPROTO_IPV6: X(afinfo, type, ipip6); break; default: WARN_ON(1); break; } #undef X rcu_read_unlock(); } EXPORT_SYMBOL(xfrm_unregister_type); static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family) { const struct xfrm_type *type = NULL; struct xfrm_state_afinfo *afinfo; int modload_attempted = 0; retry: afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return NULL; switch (proto) { case IPPROTO_COMP: type = afinfo->type_comp; break; case IPPROTO_AH: type = afinfo->type_ah; break; case IPPROTO_ESP: type = afinfo->type_esp; break; case IPPROTO_IPIP: type = afinfo->type_ipip; break; case IPPROTO_DSTOPTS: type = afinfo->type_dstopts; break; case IPPROTO_ROUTING: type = afinfo->type_routing; break; case IPPROTO_IPV6: type = afinfo->type_ipip6; break; default: break; } if (unlikely(type && !try_module_get(type->owner))) type = NULL; rcu_read_unlock(); if (!type && !modload_attempted) { request_module("xfrm-type-%d-%d", family, proto); modload_attempted = 1; goto retry; } return type; } static void xfrm_put_type(const struct xfrm_type *type) { module_put(type->owner); } int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); int err = 0; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; switch (type->proto) { case IPPROTO_ESP: WARN_ON(afinfo->type_offload_esp); afinfo->type_offload_esp = type; break; default: WARN_ON(1); err = -EPROTONOSUPPORT; break; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(xfrm_register_type_offload); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return; switch (type->proto) { case IPPROTO_ESP: WARN_ON(afinfo->type_offload_esp != type); afinfo->type_offload_esp = NULL; break; default: WARN_ON(1); break; } rcu_read_unlock(); } EXPORT_SYMBOL(xfrm_unregister_type_offload); static const struct xfrm_type_offload * xfrm_get_type_offload(u8 proto, unsigned short family, bool try_load) { const struct xfrm_type_offload *type = NULL; struct xfrm_state_afinfo *afinfo; retry: afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return NULL; switch (proto) { case IPPROTO_ESP: type = afinfo->type_offload_esp; break; default: break; } if ((type && !try_module_get(type->owner))) type = NULL; rcu_read_unlock(); if (!type && try_load) { request_module("xfrm-offload-%d-%d", family, proto); try_load = false; goto retry; } return type; } static void xfrm_put_type_offload(const struct xfrm_type_offload *type) { module_put(type->owner); } static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = { [XFRM_MODE_BEET] = { .encap = XFRM_MODE_BEET, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, [XFRM_MODE_TRANSPORT] = { .encap = XFRM_MODE_TRANSPORT, .family = AF_INET, }, [XFRM_MODE_TUNNEL] = { .encap = XFRM_MODE_TUNNEL, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, }; static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = { [XFRM_MODE_BEET] = { .encap = XFRM_MODE_BEET, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, [XFRM_MODE_ROUTEOPTIMIZATION] = { .encap = XFRM_MODE_ROUTEOPTIMIZATION, .family = AF_INET6, }, [XFRM_MODE_TRANSPORT] = { .encap = XFRM_MODE_TRANSPORT, .family = AF_INET6, }, [XFRM_MODE_TUNNEL] = { .encap = XFRM_MODE_TUNNEL, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, }; static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family) { const struct xfrm_mode *mode; if (unlikely(encap >= XFRM_MODE_MAX)) return NULL; switch (family) { case AF_INET: mode = &xfrm4_mode_map[encap]; if (mode->family == family) return mode; break; case AF_INET6: mode = &xfrm6_mode_map[encap]; if (mode->family == family) return mode; break; default: break; } return NULL; } void xfrm_state_free(struct xfrm_state *x) { kmem_cache_free(xfrm_state_cache, x); } EXPORT_SYMBOL(xfrm_state_free); static void ___xfrm_state_destroy(struct xfrm_state *x) { hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); kfree(x->aead); kfree(x->aalg); kfree(x->ealg); kfree(x->calg); kfree(x->encap); kfree(x->coaddr); kfree(x->replay_esn); kfree(x->preplay_esn); if (x->type_offload) xfrm_put_type_offload(x->type_offload); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); } if (x->xfrag.page) put_page(x->xfrag.page); xfrm_dev_state_free(x); security_xfrm_state_free(x); xfrm_state_free(x); } static void xfrm_state_gc_task(struct work_struct *work) { struct xfrm_state *x; struct hlist_node *tmp; struct hlist_head gc_list; spin_lock_bh(&xfrm_state_gc_lock); hlist_move_list(&xfrm_state_gc_list, &gc_list); spin_unlock_bh(&xfrm_state_gc_lock); synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) ___xfrm_state_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) { struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer); enum hrtimer_restart ret = HRTIMER_NORESTART; time64_t now = ktime_get_real_seconds(); time64_t next = TIME64_MAX; int warn = 0; int err = 0; spin_lock(&x->lock); xfrm_dev_state_update_stats(x); if (x->km.state == XFRM_STATE_DEAD) goto out; if (x->km.state == XFRM_STATE_EXPIRED) goto expired; if (x->lft.hard_add_expires_seconds) { time64_t tmo = x->lft.hard_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { if (x->xflags & XFRM_SOFT_EXPIRE) { /* enter hard expire without soft expire first?! * setting a new date could trigger this. * workaround: fix x->curflt.add_time by below: */ x->curlft.add_time = now - x->saved_tmo - 1; tmo = x->lft.hard_add_expires_seconds - x->saved_tmo; } else goto expired; } if (tmo < next) next = tmo; } if (x->lft.hard_use_expires_seconds) { time64_t tmo = x->lft.hard_use_expires_seconds + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (x->km.dying) goto resched; if (x->lft.soft_add_expires_seconds) { time64_t tmo = x->lft.soft_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { warn = 1; x->xflags &= ~XFRM_SOFT_EXPIRE; } else if (tmo < next) { next = tmo; x->xflags |= XFRM_SOFT_EXPIRE; x->saved_tmo = tmo; } } if (x->lft.soft_use_expires_seconds) { time64_t tmo = x->lft.soft_use_expires_seconds + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) warn = 1; else if (tmo < next) next = tmo; } x->km.dying = warn; if (warn) km_state_expired(x, 0, 0); resched: if (next != TIME64_MAX) { hrtimer_forward_now(&x->mtimer, ktime_set(next, 0)); ret = HRTIMER_RESTART; } goto out; expired: if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) x->km.state = XFRM_STATE_EXPIRED; err = __xfrm_state_delete(x); if (!err) km_state_expired(x, 1, 0); xfrm_audit_state_delete(x, err ? 0 : 1, true); out: spin_unlock(&x->lock); return ret; } static void xfrm_replay_timer_handler(struct timer_list *t); struct xfrm_state *xfrm_state_alloc(struct net *net) { struct xfrm_state *x; x = kmem_cache_zalloc(xfrm_state_cache, GFP_ATOMIC); if (x) { write_pnet(&x->xs_net, net); refcount_set(&x->refcnt, 1); atomic_set(&x->tunnel_users, 0); INIT_LIST_HEAD(&x->km.all); INIT_HLIST_NODE(&x->bydst); INIT_HLIST_NODE(&x->bysrc); INIT_HLIST_NODE(&x->byspi); INIT_HLIST_NODE(&x->byseq); hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT); x->mtimer.function = xfrm_timer_handler; timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0); x->curlft.add_time = ktime_get_real_seconds(); x->lft.soft_byte_limit = XFRM_INF; x->lft.soft_packet_limit = XFRM_INF; x->lft.hard_byte_limit = XFRM_INF; x->lft.hard_packet_limit = XFRM_INF; x->replay_maxage = 0; x->replay_maxdiff = 0; spin_lock_init(&x->lock); } return x; } EXPORT_SYMBOL(xfrm_state_alloc); #ifdef CONFIG_XFRM_OFFLOAD void xfrm_dev_state_delete(struct xfrm_state *x) { struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = READ_ONCE(xso->dev); if (dev) { dev->xfrmdev_ops->xdo_dev_state_delete(x); spin_lock_bh(&xfrm_state_dev_gc_lock); hlist_add_head(&x->dev_gclist, &xfrm_state_dev_gc_list); spin_unlock_bh(&xfrm_state_dev_gc_lock); } } EXPORT_SYMBOL_GPL(xfrm_dev_state_delete); void xfrm_dev_state_free(struct xfrm_state *x) { struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = READ_ONCE(xso->dev); if (dev && dev->xfrmdev_ops) { spin_lock_bh(&xfrm_state_dev_gc_lock); if (!hlist_unhashed(&x->dev_gclist)) hlist_del(&x->dev_gclist); spin_unlock_bh(&xfrm_state_dev_gc_lock); if (dev->xfrmdev_ops->xdo_dev_state_free) dev->xfrmdev_ops->xdo_dev_state_free(x); WRITE_ONCE(xso->dev, NULL); xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; netdev_put(dev, &xso->dev_tracker); } } #endif void __xfrm_state_destroy(struct xfrm_state *x, bool sync) { WARN_ON(x->km.state != XFRM_STATE_DEAD); if (sync) { synchronize_rcu(); ___xfrm_state_destroy(x); } else { spin_lock_bh(&xfrm_state_gc_lock); hlist_add_head(&x->gclist, &xfrm_state_gc_list); spin_unlock_bh(&xfrm_state_gc_lock); schedule_work(&xfrm_state_gc_work); } } EXPORT_SYMBOL(__xfrm_state_destroy); int __xfrm_state_delete(struct xfrm_state *x) { struct net *net = xs_net(x); int err = -ESRCH; if (x->km.state != XFRM_STATE_DEAD) { x->km.state = XFRM_STATE_DEAD; spin_lock(&net->xfrm.xfrm_state_lock); list_del(&x->km.all); hlist_del_rcu(&x->bydst); hlist_del_rcu(&x->bysrc); if (x->km.seq) hlist_del_rcu(&x->byseq); if (x->id.spi) hlist_del_rcu(&x->byspi); net->xfrm.state_num--; xfrm_nat_keepalive_state_updated(x); spin_unlock(&net->xfrm.xfrm_state_lock); if (x->encap_sk) sock_put(rcu_dereference_raw(x->encap_sk)); xfrm_dev_state_delete(x); /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that * is what we are dropping here. */ xfrm_state_put(x); err = 0; } return err; } EXPORT_SYMBOL(__xfrm_state_delete); int xfrm_state_delete(struct xfrm_state *x) { int err; spin_lock_bh(&x->lock); err = __xfrm_state_delete(x); spin_unlock_bh(&x->lock); return err; } EXPORT_SYMBOL(xfrm_state_delete); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { int i, err = 0; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (xfrm_id_proto_match(x->id.proto, proto) && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, task_valid); return err; } } } return err; } static inline int xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { int i, err = 0; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; struct xfrm_dev_offload *xso; hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { xso = &x->xso; if (xso->dev == dev && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, task_valid); return err; } } } return err; } #else static inline int xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { return 0; } static inline int xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { return 0; } #endif int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) { int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_flush_secctx_check(net, proto, task_valid); if (err) goto out; err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; restart: hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); if (sync) xfrm_state_put_sync(x); else xfrm_state_put(x); if (!err) cnt++; spin_lock_bh(&net->xfrm.xfrm_state_lock); goto restart; } } } out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (cnt) err = 0; return err; } EXPORT_SYMBOL(xfrm_state_flush); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid) { struct xfrm_state *x; struct hlist_node *tmp; struct xfrm_dev_offload *xso; int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_dev_state_flush_secctx_check(net, dev, task_valid); if (err) goto out; err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { restart: hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { xso = &x->xso; if (!xfrm_state_kern(x) && xso->dev == dev) { xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); xfrm_dev_state_free(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); xfrm_state_put(x); if (!err) cnt++; spin_lock_bh(&net->xfrm.xfrm_state_lock); goto restart; } } } if (cnt) err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); spin_lock_bh(&xfrm_state_dev_gc_lock); restart_gc: hlist_for_each_entry_safe(x, tmp, &xfrm_state_dev_gc_list, dev_gclist) { xso = &x->xso; if (xso->dev == dev) { spin_unlock_bh(&xfrm_state_dev_gc_lock); xfrm_dev_state_free(x); spin_lock_bh(&xfrm_state_dev_gc_lock); goto restart_gc; } } spin_unlock_bh(&xfrm_state_dev_gc_lock); xfrm_flush_gc(); return err; } EXPORT_SYMBOL(xfrm_dev_state_flush); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; si->sadhcnt = net->xfrm.state_hmask + 1; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_sad_getinfo); static void __xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi4 *fl4 = &fl->u.ip4; sel->daddr.a4 = fl4->daddr; sel->saddr.a4 = fl4->saddr; sel->dport = xfrm_flowi_dport(fl, &fl4->uli); sel->dport_mask = htons(0xffff); sel->sport = xfrm_flowi_sport(fl, &fl4->uli); sel->sport_mask = htons(0xffff); sel->family = AF_INET; sel->prefixlen_d = 32; sel->prefixlen_s = 32; sel->proto = fl4->flowi4_proto; sel->ifindex = fl4->flowi4_oif; } static void __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi6 *fl6 = &fl->u.ip6; /* Initialize temporary selector matching only to current session. */ *(struct in6_addr *)&sel->daddr = fl6->daddr; *(struct in6_addr *)&sel->saddr = fl6->saddr; sel->dport = xfrm_flowi_dport(fl, &fl6->uli); sel->dport_mask = htons(0xffff); sel->sport = xfrm_flowi_sport(fl, &fl6->uli); sel->sport_mask = htons(0xffff); sel->family = AF_INET6; sel->prefixlen_d = 128; sel->prefixlen_s = 128; sel->proto = fl6->flowi6_proto; sel->ifindex = fl6->flowi6_oif; } static void xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl, const struct xfrm_tmpl *tmpl, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { switch (family) { case AF_INET: __xfrm4_init_tempsel(&x->sel, fl); break; case AF_INET6: __xfrm6_init_tempsel(&x->sel, fl); break; } x->id = tmpl->id; switch (tmpl->encap_family) { case AF_INET: if (x->id.daddr.a4 == 0) x->id.daddr.a4 = daddr->a4; x->props.saddr = tmpl->saddr; if (x->props.saddr.a4 == 0) x->props.saddr.a4 = saddr->a4; break; case AF_INET6: if (ipv6_addr_any((struct in6_addr *)&x->id.daddr)) memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr)); memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr)); if (ipv6_addr_any((struct in6_addr *)&x->props.saddr)) memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr)); break; } x->props.mode = tmpl->mode; x->props.reqid = tmpl->reqid; x->props.family = tmpl->encap_family; } static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, struct xfrm_dev_offload *xdo) { unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); struct xfrm_state *x; hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) { #ifdef CONFIG_XFRM_OFFLOAD if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) /* HW states are in the head of list, there is * no need to iterate further. */ break; /* Packet offload: both policy and SA should * have same device. */ if (xdo->dev != x->xso.dev) continue; } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) /* Skip HW policy for SW lookups */ continue; #endif if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); struct xfrm_state *x; hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { unsigned int h = xfrm_src_hash(net, daddr, saddr, family); struct xfrm_state *x; hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) { if (x->props.family != family || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family) || !xfrm_addr_equal(&x->props.saddr, saddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } static inline struct xfrm_state * __xfrm_state_locate(struct xfrm_state *x, int use_spi, int family) { struct net *net = xs_net(x); u32 mark = x->mark.v & x->mark.m; if (use_spi) return __xfrm_state_lookup(net, mark, &x->id.daddr, x->id.spi, x->id.proto, family); else return __xfrm_state_lookup_byaddr(net, mark, &x->id.daddr, &x->props.saddr, x->id.proto, family); } static void xfrm_hash_grow_check(struct net *net, int have_hash_collision) { if (have_hash_collision && (net->xfrm.state_hmask + 1) < xfrm_state_hashmax && net->xfrm.state_num > net->xfrm.state_hmask) schedule_work(&net->xfrm.state_hash_work); } static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, const struct flowi *fl, unsigned short family, struct xfrm_state **best, int *acq_in_progress, int *error) { /* Resolution logic: * 1. There is a valid state with matching selector. Done. * 2. Valid state with inappropriate selector. Skip. * * Entering area of "sysdeps". * * 3. If state is not valid, selector is temporary, it selects * only session which triggered previous resolution. Key * manager will do something to install a state with proper * selector. */ if (x->km.state == XFRM_STATE_VALID) { if ((x->sel.family && (x->sel.family != family || !xfrm_selector_match(&x->sel, fl, family))) || !security_xfrm_state_pol_flow_match(x, pol, &fl->u.__fl_common)) return; if (!*best || (*best)->km.dying > x->km.dying || ((*best)->km.dying == x->km.dying && (*best)->curlft.add_time < x->curlft.add_time)) *best = x; } else if (x->km.state == XFRM_STATE_ACQ) { *acq_in_progress = 1; } else if (x->km.state == XFRM_STATE_ERROR || x->km.state == XFRM_STATE_EXPIRED) { if ((!x->sel.family || (x->sel.family == family && xfrm_selector_match(&x->sel, fl, family))) && security_xfrm_state_pol_flow_match(x, pol, &fl->u.__fl_common)) *error = -ESRCH; } } struct xfrm_state * xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family, u32 if_id) { static xfrm_address_t saddr_wildcard = { }; struct net *net = xp_net(pol); unsigned int h, h_wildcard; struct xfrm_state *x, *x0, *to_put; int acquire_in_progress = 0; int error = 0; struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; unsigned short encap_family = tmpl->encap_family; unsigned int sequence; struct km_event c; to_put = NULL; sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); rcu_read_lock(); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) { #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) /* HW states are in the head of list, there is * no need to iterate further. */ break; /* Packet offload: both policy and SA should * have same device. */ if (pol->xdo.dev != x->xso.dev) continue; } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) /* Skip HW policy for SW lookups */ continue; #endif if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error); } if (best || acquire_in_progress) goto found; h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) { #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) /* HW states are in the head of list, there is * no need to iterate further. */ break; /* Packet offload: both policy and SA should * have same device. */ if (pol->xdo.dev != x->xso.dev) continue; } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) /* Skip HW policy for SW lookups */ continue; #endif if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_addr_equal(&x->id.daddr, daddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error); } found: x = best; if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && (x0 = __xfrm_state_lookup_all(net, mark, daddr, tmpl->id.spi, tmpl->id.proto, encap_family, &pol->xdo)) != NULL) { to_put = x0; error = -EEXIST; goto out; } c.net = net; /* If the KMs have no listeners (yet...), avoid allocating an SA * for each and every packet - garbage collection might not * handle the flood. */ if (!km_is_alive(&c)) { error = -ESRCH; goto out; } x = xfrm_state_alloc(net); if (x == NULL) { error = -ENOMEM; goto out; } /* Initialize temporary state matching only * to current session. */ xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family); memcpy(&x->mark, &pol->mark, sizeof(x->mark)); x->if_id = if_id; error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid); if (error) { x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; goto out; } #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { struct xfrm_dev_offload *xdo = &pol->xdo; struct xfrm_dev_offload *xso = &x->xso; xso->type = XFRM_DEV_OFFLOAD_PACKET; xso->dir = xdo->dir; xso->dev = xdo->dev; xso->real_dev = xdo->real_dev; xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ; netdev_hold(xso->dev, &xso->dev_tracker, GFP_ATOMIC); error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x, NULL); if (error) { xso->dir = 0; netdev_put(xso->dev, &xso->dev_tracker); xso->dev = NULL; xso->real_dev = NULL; xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; goto out; } } #endif if (km_query(x, tmpl, pol) == 0) { spin_lock_bh(&net->xfrm.xfrm_state_lock); x->km.state = XFRM_STATE_ACQ; x->dir = XFRM_SA_DIR_OUT; list_add(&x->km.all, &net->xfrm.state_all); XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, x->xso.type); h = xfrm_src_hash(net, daddr, saddr, encap_family); XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, x->xso.type); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h, x->xso.type); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } else { #ifdef CONFIG_XFRM_OFFLOAD struct xfrm_dev_offload *xso = &x->xso; if (xso->type == XFRM_DEV_OFFLOAD_PACKET) { xfrm_dev_state_delete(x); xfrm_dev_state_free(x); } #endif x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; error = -ESRCH; } } out: if (x) { if (!xfrm_state_hold_rcu(x)) { *err = -EAGAIN; x = NULL; } } else { *err = acquire_in_progress ? -EAGAIN : error; } rcu_read_unlock(); if (to_put) xfrm_state_put(to_put); if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) { *err = -EAGAIN; if (x) { xfrm_state_put(x); x = NULL; } } return x; } struct xfrm_state * xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid) { unsigned int h; struct xfrm_state *rx = NULL, *x = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, family) && mode == x->props.mode && proto == x->id.proto && x->km.state == XFRM_STATE_VALID) { rx = x; break; } } if (rx) xfrm_state_hold(rx); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return rx; } EXPORT_SYMBOL(xfrm_stateonly_find); struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, unsigned short family) { struct xfrm_state *x; struct xfrm_state_walk *w; spin_lock_bh(&net->xfrm.xfrm_state_lock); list_for_each_entry(w, &net->xfrm.state_all, all) { x = container_of(w, struct xfrm_state, km); if (x->props.family != family || x->id.spi != spi) continue; xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } spin_unlock_bh(&net->xfrm.xfrm_state_lock); return NULL; } EXPORT_SYMBOL(xfrm_state_lookup_byspi); static void __xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); unsigned int h; list_add(&x->km.all, &net->xfrm.state_all); h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, x->xso.type); h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family); XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, x->xso.type); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h, x->xso.type); } hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); xfrm_nat_keepalive_state_updated(x); } /* net->xfrm.xfrm_state_lock is held */ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) { struct net *net = xs_net(xnew); unsigned short family = xnew->props.family; u32 reqid = xnew->props.reqid; struct xfrm_state *x; unsigned int h; u32 mark = xnew->mark.v & xnew->mark.m; u32 if_id = xnew->if_id; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && x->if_id == if_id && (mark & x->mark.m) == x->mark.v && xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) && xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family)) x->genid++; } } void xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); spin_lock_bh(&net->xfrm.xfrm_state_lock); __xfrm_state_bump_genids(x); __xfrm_state_insert(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_insert); /* net->xfrm.xfrm_state_lock is held */ static struct xfrm_state *__find_acq_core(struct net *net, const struct xfrm_mark *m, unsigned short family, u8 mode, u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create) { unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family); struct xfrm_state *x; u32 mark = m->v & m->m; hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.reqid != reqid || x->props.mode != mode || x->props.family != family || x->km.state != XFRM_STATE_ACQ || x->id.spi != 0 || x->id.proto != proto || (mark & x->mark.m) != x->mark.v || !xfrm_addr_equal(&x->id.daddr, daddr, family) || !xfrm_addr_equal(&x->props.saddr, saddr, family)) continue; xfrm_state_hold(x); return x; } if (!create) return NULL; x = xfrm_state_alloc(net); if (likely(x)) { switch (family) { case AF_INET: x->sel.daddr.a4 = daddr->a4; x->sel.saddr.a4 = saddr->a4; x->sel.prefixlen_d = 32; x->sel.prefixlen_s = 32; x->props.saddr.a4 = saddr->a4; x->id.daddr.a4 = daddr->a4; break; case AF_INET6: x->sel.daddr.in6 = daddr->in6; x->sel.saddr.in6 = saddr->in6; x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; x->props.saddr.in6 = saddr->in6; x->id.daddr.in6 = daddr->in6; break; } x->km.state = XFRM_STATE_ACQ; x->id.proto = proto; x->props.family = family; x->props.mode = mode; x->props.reqid = reqid; x->if_id = if_id; x->mark.v = m->v; x->mark.m = m->m; x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; xfrm_state_hold(x); hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); list_add(&x->km.all, &net->xfrm.state_all); XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, x->xso.type); h = xfrm_src_hash(net, daddr, saddr, family); XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, x->xso.type); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); } return x; } static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); int xfrm_state_add(struct xfrm_state *x) { struct net *net = xs_net(x); struct xfrm_state *x1, *to_put; int family; int err; u32 mark = x->mark.v & x->mark.m; int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); family = x->props.family; to_put = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, family); if (x1) { to_put = x1; x1 = NULL; err = -EEXIST; goto out; } if (use_spi && x->km.seq) { x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq); if (x1 && ((x1->id.proto != x->id.proto) || !xfrm_addr_equal(&x1->id.daddr, &x->id.daddr, family))) { to_put = x1; x1 = NULL; } } if (use_spi && !x1) x1 = __find_acq_core(net, &x->mark, family, x->props.mode, x->props.reqid, x->if_id, x->id.proto, &x->id.daddr, &x->props.saddr, 0); __xfrm_state_bump_genids(x); __xfrm_state_insert(x); err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (x1) { xfrm_state_delete(x1); xfrm_state_put(x1); } if (to_put) xfrm_state_put(to_put); return err; } EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security) { struct xfrm_user_sec_ctx *uctx; int size = sizeof(*uctx) + security->ctx_len; int err; uctx = kmalloc(size, GFP_KERNEL); if (!uctx) return -ENOMEM; uctx->exttype = XFRMA_SEC_CTX; uctx->len = size; uctx->ctx_doi = security->ctx_doi; uctx->ctx_alg = security->ctx_alg; uctx->ctx_len = security->ctx_len; memcpy(uctx + 1, security->ctx_str, security->ctx_len); err = security_xfrm_state_alloc(x, uctx); kfree(uctx); if (err) return err; return 0; } static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, struct xfrm_encap_tmpl *encap) { struct net *net = xs_net(orig); struct xfrm_state *x = xfrm_state_alloc(net); if (!x) goto out; memcpy(&x->id, &orig->id, sizeof(x->id)); memcpy(&x->sel, &orig->sel, sizeof(x->sel)); memcpy(&x->lft, &orig->lft, sizeof(x->lft)); x->props.mode = orig->props.mode; x->props.replay_window = orig->props.replay_window; x->props.reqid = orig->props.reqid; x->props.family = orig->props.family; x->props.saddr = orig->props.saddr; if (orig->aalg) { x->aalg = xfrm_algo_auth_clone(orig->aalg); if (!x->aalg) goto error; } x->props.aalgo = orig->props.aalgo; if (orig->aead) { x->aead = xfrm_algo_aead_clone(orig->aead); x->geniv = orig->geniv; if (!x->aead) goto error; } if (orig->ealg) { x->ealg = xfrm_algo_clone(orig->ealg); if (!x->ealg) goto error; } x->props.ealgo = orig->props.ealgo; if (orig->calg) { x->calg = xfrm_algo_clone(orig->calg); if (!x->calg) goto error; } x->props.calgo = orig->props.calgo; if (encap || orig->encap) { if (encap) x->encap = kmemdup(encap, sizeof(*x->encap), GFP_KERNEL); else x->encap = kmemdup(orig->encap, sizeof(*x->encap), GFP_KERNEL); if (!x->encap) goto error; } if (orig->security) if (clone_security(x, orig->security)) goto error; if (orig->coaddr) { x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr), GFP_KERNEL); if (!x->coaddr) goto error; } if (orig->replay_esn) { if (xfrm_replay_clone(x, orig)) goto error; } memcpy(&x->mark, &orig->mark, sizeof(x->mark)); memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark)); x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; x->if_id = orig->if_id; x->tfcpad = orig->tfcpad; x->replay_maxdiff = orig->replay_maxdiff; x->replay_maxage = orig->replay_maxage; memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft)); x->km.state = orig->km.state; x->km.seq = orig->km.seq; x->replay = orig->replay; x->preplay = orig->preplay; x->mapping_maxage = orig->mapping_maxage; x->lastused = orig->lastused; x->new_mapping = 0; x->new_mapping_sport = 0; x->dir = orig->dir; return x; error: xfrm_state_put(x); out: return NULL; } struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, u32 if_id) { unsigned int h; struct xfrm_state *x = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); if (m->reqid) { h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, m->reqid, m->old_family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; if (m->reqid && x->props.reqid != m->reqid) continue; if (if_id != 0 && x->if_id != if_id) continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, m->old_family)) continue; xfrm_state_hold(x); break; } } else { h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, m->old_family); hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; if (if_id != 0 && x->if_id != if_id) continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, m->old_family)) continue; xfrm_state_hold(x); break; } } spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_migrate_state_find); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, struct xfrm_encap_tmpl *encap) { struct xfrm_state *xc; xc = xfrm_state_clone(x, encap); if (!xc) return NULL; xc->props.family = m->new_family; if (xfrm_init_state(xc) < 0) goto error; memcpy(&xc->id.daddr, &m->new_daddr, sizeof(xc->id.daddr)); memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr)); /* add state */ if (xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) { /* a care is needed when the destination address of the state is to be updated as it is a part of triplet */ xfrm_state_insert(xc); } else { if (xfrm_state_add(xc) < 0) goto error; } return xc; error: xfrm_state_put(xc); return NULL; } EXPORT_SYMBOL(xfrm_state_migrate); #endif int xfrm_state_update(struct xfrm_state *x) { struct xfrm_state *x1, *to_put; int err; int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); struct net *net = xs_net(x); to_put = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, x->props.family); err = -ESRCH; if (!x1) goto out; if (xfrm_state_kern(x1)) { to_put = x1; err = -EEXIST; goto out; } if (x1->km.state == XFRM_STATE_ACQ) { if (x->dir && x1->dir != x->dir) goto out; __xfrm_state_insert(x); x = NULL; } else { if (x1->dir != x->dir) goto out; } err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (to_put) xfrm_state_put(to_put); if (err) return err; if (!x) { xfrm_state_delete(x1); xfrm_state_put(x1); return 0; } err = -EINVAL; spin_lock_bh(&x1->lock); if (likely(x1->km.state == XFRM_STATE_VALID)) { if (x->encap && x1->encap && x->encap->encap_type == x1->encap->encap_type) memcpy(x1->encap, x->encap, sizeof(*x1->encap)); else if (x->encap || x1->encap) goto fail; if (x->coaddr && x1->coaddr) { memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr)); } if (!use_spi && memcmp(&x1->sel, &x->sel, sizeof(x1->sel))) memcpy(&x1->sel, &x->sel, sizeof(x1->sel)); memcpy(&x1->lft, &x->lft, sizeof(x1->lft)); x1->km.dying = 0; hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (READ_ONCE(x1->curlft.use_time)) xfrm_state_check_expire(x1); if (x->props.smark.m || x->props.smark.v || x->if_id) { spin_lock_bh(&net->xfrm.xfrm_state_lock); if (x->props.smark.m || x->props.smark.v) x1->props.smark = x->props.smark; if (x->if_id) x1->if_id = x->if_id; __xfrm_state_bump_genids(x1); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } err = 0; x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); } fail: spin_unlock_bh(&x1->lock); xfrm_state_put(x1); return err; } EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { xfrm_dev_state_update_stats(x); if (!READ_ONCE(x->curlft.use_time)) WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT); return -EINVAL; } if (!x->km.dying && (x->curlft.bytes >= x->lft.soft_byte_limit || x->curlft.packets >= x->lft.soft_packet_limit)) { x->km.dying = 1; km_state_expired(x, 0, 0); } return 0; } EXPORT_SYMBOL(xfrm_state_check_expire); void xfrm_state_update_stats(struct net *net) { struct xfrm_state *x; int i; spin_lock_bh(&net->xfrm.xfrm_state_lock); for (i = 0; i <= net->xfrm.state_hmask; i++) { hlist_for_each_entry(x, net->xfrm.state_bydst + i, bydst) xfrm_dev_state_update_stats(x); } spin_unlock_bh(&net->xfrm.xfrm_state_lock); } struct xfrm_state * xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { struct xfrm_state *x; rcu_read_lock(); x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family); rcu_read_unlock(); return x; } EXPORT_SYMBOL(xfrm_state_lookup); struct xfrm_state * xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_state_lookup_byaddr); struct xfrm_state * xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __find_acq_core(net, mark, family, mode, reqid, if_id, proto, daddr, saddr, create); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_find_acq); #ifdef CONFIG_XFRM_SUB_POLICY #if IS_ENABLED(CONFIG_IPV6) /* distribution counting sort function for xfrm_state and xfrm_tmpl */ static void __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(const void *p), int maxclass) { int count[XFRM_MAX_DEPTH] = { }; int class[XFRM_MAX_DEPTH]; int i; for (i = 0; i < n; i++) { int c = cmp(src[i]); class[i] = c; count[c]++; } for (i = 2; i < maxclass; i++) count[i] += count[i - 1]; for (i = 0; i < n; i++) { dst[count[class[i] - 1]++] = src[i]; src[i] = NULL; } } /* Rule for xfrm_state: * * rule 1: select IPsec transport except AH * rule 2: select MIPv6 RO or inbound trigger * rule 3: select IPsec transport AH * rule 4: select IPsec tunnel * rule 5: others */ static int __xfrm6_state_sort_cmp(const void *p) { const struct xfrm_state *v = p; switch (v->props.mode) { case XFRM_MODE_TRANSPORT: if (v->id.proto != IPPROTO_AH) return 1; else return 3; #if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; #endif case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: return 4; } return 5; } /* Rule for xfrm_tmpl: * * rule 1: select IPsec transport * rule 2: select MIPv6 RO or inbound trigger * rule 3: select IPsec tunnel * rule 4: others */ static int __xfrm6_tmpl_sort_cmp(const void *p) { const struct xfrm_tmpl *v = p; switch (v->mode) { case XFRM_MODE_TRANSPORT: return 1; #if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; #endif case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: return 3; } return 4; } #else static inline int __xfrm6_state_sort_cmp(const void *p) { return 5; } static inline int __xfrm6_tmpl_sort_cmp(const void *p) { return 4; } static inline void __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(const void *p), int maxclass) { int i; for (i = 0; i < n; i++) dst[i] = src[i]; } #endif /* CONFIG_IPV6 */ void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family) { int i; if (family == AF_INET6) __xfrm6_sort((void **)dst, (void **)src, n, __xfrm6_tmpl_sort_cmp, 5); else for (i = 0; i < n; i++) dst[i] = src[i]; } void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, unsigned short family) { int i; if (family == AF_INET6) __xfrm6_sort((void **)dst, (void **)src, n, __xfrm6_state_sort_cmp, 6); else for (i = 0; i < n; i++) dst[i] = src[i]; } #endif /* Silly enough, but I'm lazy to build resolution list */ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq) { unsigned int h = xfrm_seq_hash(net, seq); struct xfrm_state *x; hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) { if (x->km.seq == seq && (mark & x->mark.m) == x->mark.v && x->km.state == XFRM_STATE_ACQ) { xfrm_state_hold(x); return x; } } return NULL; } struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_find_acq_byseq(net, mark, seq); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_find_acq_byseq); u32 xfrm_get_acqseq(void) { u32 res; static atomic_t acqseq; do { res = atomic_inc_return(&acqseq); } while (!res); return res; } EXPORT_SYMBOL(xfrm_get_acqseq); int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack) { switch (proto) { case IPPROTO_AH: case IPPROTO_ESP: break; case IPPROTO_COMP: /* IPCOMP spi is 16-bits. */ if (max >= 0x10000) { NL_SET_ERR_MSG(extack, "IPCOMP SPI must be <= 65535"); return -EINVAL; } break; default: NL_SET_ERR_MSG(extack, "Invalid protocol, must be one of AH, ESP, IPCOMP"); return -EINVAL; } if (min > max) { NL_SET_ERR_MSG(extack, "Invalid SPI range: min > max"); return -EINVAL; } return 0; } EXPORT_SYMBOL(verify_spi_info); int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, struct netlink_ext_ack *extack) { struct net *net = xs_net(x); unsigned int h; struct xfrm_state *x0; int err = -ENOENT; __be32 minspi = htonl(low); __be32 maxspi = htonl(high); __be32 newspi = 0; u32 mark = x->mark.v & x->mark.m; spin_lock_bh(&x->lock); if (x->km.state == XFRM_STATE_DEAD) { NL_SET_ERR_MSG(extack, "Target ACQUIRE is in DEAD state"); goto unlock; } err = 0; if (x->id.spi) goto unlock; err = -ENOENT; if (minspi == maxspi) { x0 = xfrm_state_lookup(net, mark, &x->id.daddr, minspi, x->id.proto, x->props.family); if (x0) { NL_SET_ERR_MSG(extack, "Requested SPI is already in use"); xfrm_state_put(x0); goto unlock; } newspi = minspi; } else { u32 spi = 0; for (h = 0; h < high-low+1; h++) { spi = get_random_u32_inclusive(low, high); x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { newspi = htonl(spi); break; } xfrm_state_put(x0); } } if (newspi) { spin_lock_bh(&net->xfrm.xfrm_state_lock); x->id.spi = newspi; h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; } else { NL_SET_ERR_MSG(extack, "No SPI available in the requested range"); } unlock: spin_unlock_bh(&x->lock); return err; } EXPORT_SYMBOL(xfrm_alloc_spi); static bool __xfrm_state_filter_match(struct xfrm_state *x, struct xfrm_address_filter *filter) { if (filter) { if ((filter->family == AF_INET || filter->family == AF_INET6) && x->props.family != filter->family) return false; return addr_match(&x->props.saddr, &filter->saddr, filter->splen) && addr_match(&x->id.daddr, &filter->daddr, filter->dplen); } return true; } int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *data) { struct xfrm_state *state; struct xfrm_state_walk *x; int err = 0; if (walk->seq != 0 && list_empty(&walk->all)) return 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); if (list_empty(&walk->all)) x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all); else x = list_first_entry(&walk->all, struct xfrm_state_walk, all); list_for_each_entry_from(x, &net->xfrm.state_all, all) { if (x->state == XFRM_STATE_DEAD) continue; state = container_of(x, struct xfrm_state, km); if (!xfrm_id_proto_match(state->id.proto, walk->proto)) continue; if (!__xfrm_state_filter_match(state, walk->filter)) continue; err = func(state, walk->seq, data); if (err) { list_move_tail(&walk->all, &x->all); goto out; } walk->seq++; } if (walk->seq == 0) { err = -ENOENT; goto out; } list_del_init(&walk->all); out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_state_walk); void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, struct xfrm_address_filter *filter) { INIT_LIST_HEAD(&walk->all); walk->proto = proto; walk->state = XFRM_STATE_DEAD; walk->seq = 0; walk->filter = filter; } EXPORT_SYMBOL(xfrm_state_walk_init); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net) { kfree(walk->filter); if (list_empty(&walk->all)) return; spin_lock_bh(&net->xfrm.xfrm_state_lock); list_del(&walk->all); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_walk_done); static void xfrm_replay_timer_handler(struct timer_list *t) { struct xfrm_state *x = from_timer(x, t, rtimer); spin_lock(&x->lock); if (x->km.state == XFRM_STATE_VALID) { if (xfrm_aevent_is_on(xs_net(x))) xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT); else x->xflags |= XFRM_TIME_DEFER; } spin_unlock(&x->lock); } static LIST_HEAD(xfrm_km_list); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify_policy) km->notify_policy(xp, dir, c); rcu_read_unlock(); } void km_state_notify(struct xfrm_state *x, const struct km_event *c) { struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify) km->notify(x, c); rcu_read_unlock(); } EXPORT_SYMBOL(km_policy_notify); EXPORT_SYMBOL(km_state_notify); void km_state_expired(struct xfrm_state *x, int hard, u32 portid) { struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_EXPIRE; km_state_notify(x, &c); } EXPORT_SYMBOL(km_state_expired); /* * We send to all registered managers regardless of failure * We are happy with one success */ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) { int err = -EINVAL, acqret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { acqret = km->acquire(x, t, pol); if (!acqret) err = acqret; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_query); static int __km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { int err = -EINVAL; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->new_mapping) err = km->new_mapping(x, ipaddr, sport); if (!err) break; } rcu_read_unlock(); return err; } int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { int ret = 0; if (x->mapping_maxage) { if ((jiffies / HZ - x->new_mapping) > x->mapping_maxage || x->new_mapping_sport != sport) { x->new_mapping_sport = sport; x->new_mapping = jiffies / HZ; ret = __km_new_mapping(x, ipaddr, sport); } } else { ret = __km_new_mapping(x, ipaddr, sport); } return ret; } EXPORT_SYMBOL(km_new_mapping); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid) { struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_POLEXPIRE; km_policy_notify(pol, dir, &c); } EXPORT_SYMBOL(km_policy_expired); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap) { int err = -EINVAL; int ret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->migrate) { ret = km->migrate(sel, dir, type, m, num_migrate, k, encap); if (!ret) err = ret; } } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_migrate); #endif int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) { int err = -EINVAL; int ret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->report) { ret = km->report(net, proto, sel, addr); if (!ret) err = ret; } } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_report); static bool km_is_alive(const struct km_event *c) { struct xfrm_mgr *km; bool is_alive = false; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->is_alive && km->is_alive(c)) { is_alive = true; break; } } rcu_read_unlock(); return is_alive; } #if IS_ENABLED(CONFIG_XFRM_USER_COMPAT) static DEFINE_SPINLOCK(xfrm_translator_lock); static struct xfrm_translator __rcu *xfrm_translator; struct xfrm_translator *xfrm_get_translator(void) { struct xfrm_translator *xtr; rcu_read_lock(); xtr = rcu_dereference(xfrm_translator); if (unlikely(!xtr)) goto out; if (!try_module_get(xtr->owner)) xtr = NULL; out: rcu_read_unlock(); return xtr; } EXPORT_SYMBOL_GPL(xfrm_get_translator); void xfrm_put_translator(struct xfrm_translator *xtr) { module_put(xtr->owner); } EXPORT_SYMBOL_GPL(xfrm_put_translator); int xfrm_register_translator(struct xfrm_translator *xtr) { int err = 0; spin_lock_bh(&xfrm_translator_lock); if (unlikely(xfrm_translator != NULL)) err = -EEXIST; else rcu_assign_pointer(xfrm_translator, xtr); spin_unlock_bh(&xfrm_translator_lock); return err; } EXPORT_SYMBOL_GPL(xfrm_register_translator); int xfrm_unregister_translator(struct xfrm_translator *xtr) { int err = 0; spin_lock_bh(&xfrm_translator_lock); if (likely(xfrm_translator != NULL)) { if (rcu_access_pointer(xfrm_translator) != xtr) err = -EINVAL; else RCU_INIT_POINTER(xfrm_translator, NULL); } spin_unlock_bh(&xfrm_translator_lock); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(xfrm_unregister_translator); #endif int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) { int err; u8 *data; struct xfrm_mgr *km; struct xfrm_policy *pol = NULL; if (sockptr_is_null(optval) && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); __sk_dst_reset(sk); return 0; } if (optlen <= 0 || optlen > PAGE_SIZE) return -EMSGSIZE; data = memdup_sockptr(optval, optlen); if (IS_ERR(data)) return PTR_ERR(data); if (in_compat_syscall()) { struct xfrm_translator *xtr = xfrm_get_translator(); if (!xtr) { kfree(data); return -EOPNOTSUPP; } err = xtr->xlate_user_policy_sockptr(&data, optlen); xfrm_put_translator(xtr); if (err) { kfree(data); return err; } } err = -EINVAL; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { pol = km->compile_policy(sk, optname, data, optlen, &err); if (err >= 0) break; } rcu_read_unlock(); if (err >= 0) { xfrm_sk_policy_insert(sk, err, pol); xfrm_pol_put(pol); __sk_dst_reset(sk); err = 0; } kfree(data); return err; } EXPORT_SYMBOL(xfrm_user_policy); static DEFINE_SPINLOCK(xfrm_km_lock); void xfrm_register_km(struct xfrm_mgr *km) { spin_lock_bh(&xfrm_km_lock); list_add_tail_rcu(&km->list, &xfrm_km_list); spin_unlock_bh(&xfrm_km_lock); } EXPORT_SYMBOL(xfrm_register_km); void xfrm_unregister_km(struct xfrm_mgr *km) { spin_lock_bh(&xfrm_km_lock); list_del_rcu(&km->list); spin_unlock_bh(&xfrm_km_lock); synchronize_rcu(); } EXPORT_SYMBOL(xfrm_unregister_km); int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo) { int err = 0; if (WARN_ON(afinfo->family >= NPROTO)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_afinfo_lock); if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL)) err = -EEXIST; else rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo); spin_unlock_bh(&xfrm_state_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_state_register_afinfo); int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo) { int err = 0, family = afinfo->family; if (WARN_ON(family >= NPROTO)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_afinfo_lock); if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) { if (rcu_access_pointer(xfrm_state_afinfo[family]) != afinfo) err = -EINVAL; else RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL); } spin_unlock_bh(&xfrm_state_afinfo_lock); synchronize_rcu(); return err; } EXPORT_SYMBOL(xfrm_state_unregister_afinfo); struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family) { if (unlikely(family >= NPROTO)) return NULL; return rcu_dereference(xfrm_state_afinfo[family]); } EXPORT_SYMBOL_GPL(xfrm_state_afinfo_get_rcu); struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) { struct xfrm_state_afinfo *afinfo; if (unlikely(family >= NPROTO)) return NULL; rcu_read_lock(); afinfo = rcu_dereference(xfrm_state_afinfo[family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; } void xfrm_flush_gc(void) { flush_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(xfrm_flush_gc); /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ void xfrm_state_delete_tunnel(struct xfrm_state *x) { if (x->tunnel) { struct xfrm_state *t = x->tunnel; if (atomic_read(&t->tunnel_users) == 2) xfrm_state_delete(t); atomic_dec(&t->tunnel_users); xfrm_state_put_sync(t); x->tunnel = NULL; } } EXPORT_SYMBOL(xfrm_state_delete_tunnel); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) { const struct xfrm_type *type = READ_ONCE(x->type); struct crypto_aead *aead; u32 blksize, net_adj = 0; if (x->km.state != XFRM_STATE_VALID || !type || type->proto != IPPROTO_ESP) return mtu - x->props.header_len; aead = x->data; blksize = ALIGN(crypto_aead_blocksize(aead), 4); switch (x->props.mode) { case XFRM_MODE_TRANSPORT: case XFRM_MODE_BEET: if (x->props.family == AF_INET) net_adj = sizeof(struct iphdr); else if (x->props.family == AF_INET6) net_adj = sizeof(struct ipv6hdr); break; case XFRM_MODE_TUNNEL: break; default: WARN_ON_ONCE(1); break; } return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - net_adj) & ~(blksize - 1)) + net_adj - 2; } EXPORT_SYMBOL_GPL(xfrm_state_mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload, struct netlink_ext_ack *extack) { const struct xfrm_mode *inner_mode; const struct xfrm_mode *outer_mode; int family = x->props.family; int err; if (family == AF_INET && READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)) x->props.flags |= XFRM_STATE_NOPMTUDISC; err = -EPROTONOSUPPORT; if (x->sel.family != AF_UNSPEC) { inner_mode = xfrm_get_mode(x->props.mode, x->sel.family); if (inner_mode == NULL) { NL_SET_ERR_MSG(extack, "Requested mode not found"); goto error; } if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) && family != x->sel.family) { NL_SET_ERR_MSG(extack, "Only tunnel modes can accommodate a change of family"); goto error; } x->inner_mode = *inner_mode; } else { const struct xfrm_mode *inner_mode_iaf; int iafamily = AF_INET; inner_mode = xfrm_get_mode(x->props.mode, x->props.family); if (inner_mode == NULL) { NL_SET_ERR_MSG(extack, "Requested mode not found"); goto error; } x->inner_mode = *inner_mode; if (x->props.family == AF_INET) iafamily = AF_INET6; inner_mode_iaf = xfrm_get_mode(x->props.mode, iafamily); if (inner_mode_iaf) { if (inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL) x->inner_mode_iaf = *inner_mode_iaf; } } x->type = xfrm_get_type(x->id.proto, family); if (x->type == NULL) { NL_SET_ERR_MSG(extack, "Requested type not found"); goto error; } x->type_offload = xfrm_get_type_offload(x->id.proto, family, offload); err = x->type->init_state(x, extack); if (err) goto error; outer_mode = xfrm_get_mode(x->props.mode, family); if (!outer_mode) { NL_SET_ERR_MSG(extack, "Requested mode not found"); err = -EPROTONOSUPPORT; goto error; } x->outer_mode = *outer_mode; if (init_replay) { err = xfrm_init_replay(x, extack); if (err) goto error; } if (x->nat_keepalive_interval) { if (x->dir != XFRM_SA_DIR_OUT) { NL_SET_ERR_MSG(extack, "NAT keepalive is only supported for outbound SAs"); err = -EINVAL; goto error; } if (!x->encap || x->encap->encap_type != UDP_ENCAP_ESPINUDP) { NL_SET_ERR_MSG(extack, "NAT keepalive is only supported for UDP encapsulation"); err = -EINVAL; goto error; } } error: return err; } EXPORT_SYMBOL(__xfrm_init_state); int xfrm_init_state(struct xfrm_state *x) { int err; err = __xfrm_init_state(x, true, false, NULL); if (!err) x->km.state = XFRM_STATE_VALID; return err; } EXPORT_SYMBOL(xfrm_init_state); int __net_init xfrm_state_init(struct net *net) { unsigned int sz; if (net_eq(net, &init_net)) xfrm_state_cache = KMEM_CACHE(xfrm_state, SLAB_HWCACHE_ALIGN | SLAB_PANIC); INIT_LIST_HEAD(&net->xfrm.state_all); sz = sizeof(struct hlist_head) * 8; net->xfrm.state_bydst = xfrm_hash_alloc(sz); if (!net->xfrm.state_bydst) goto out_bydst; net->xfrm.state_bysrc = xfrm_hash_alloc(sz); if (!net->xfrm.state_bysrc) goto out_bysrc; net->xfrm.state_byspi = xfrm_hash_alloc(sz); if (!net->xfrm.state_byspi) goto out_byspi; net->xfrm.state_byseq = xfrm_hash_alloc(sz); if (!net->xfrm.state_byseq) goto out_byseq; net->xfrm.state_hmask = ((sz / sizeof(struct hlist_head)) - 1); net->xfrm.state_num = 0; INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); spin_lock_init(&net->xfrm.xfrm_state_lock); seqcount_spinlock_init(&net->xfrm.xfrm_state_hash_generation, &net->xfrm.xfrm_state_lock); return 0; out_byseq: xfrm_hash_free(net->xfrm.state_byspi, sz); out_byspi: xfrm_hash_free(net->xfrm.state_bysrc, sz); out_bysrc: xfrm_hash_free(net->xfrm.state_bydst, sz); out_bydst: return -ENOMEM; } void xfrm_state_fini(struct net *net) { unsigned int sz; flush_work(&net->xfrm.state_hash_work); flush_work(&xfrm_state_gc_work); xfrm_state_flush(net, 0, false, true); WARN_ON(!list_empty(&net->xfrm.state_all)); sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(net->xfrm.state_byseq)); xfrm_hash_free(net->xfrm.state_byseq, sz); WARN_ON(!hlist_empty(net->xfrm.state_byspi)); xfrm_hash_free(net->xfrm.state_byspi, sz); WARN_ON(!hlist_empty(net->xfrm.state_bysrc)); xfrm_hash_free(net->xfrm.state_bysrc, sz); WARN_ON(!hlist_empty(net->xfrm.state_bydst)); xfrm_hash_free(net->xfrm.state_bydst, sz); } #ifdef CONFIG_AUDITSYSCALL static void xfrm_audit_helper_sainfo(struct xfrm_state *x, struct audit_buffer *audit_buf) { struct xfrm_sec_ctx *ctx = x->security; u32 spi = ntohl(x->id.spi); if (ctx) audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); switch (x->props.family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &x->props.saddr.a4, &x->id.daddr.a4); break; case AF_INET6: audit_log_format(audit_buf, " src=%pI6 dst=%pI6", x->props.saddr.a6, x->id.daddr.a6); break; } audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi); } static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, struct audit_buffer *audit_buf) { const struct iphdr *iph4; const struct ipv6hdr *iph6; switch (family) { case AF_INET: iph4 = ip_hdr(skb); audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &iph4->saddr, &iph4->daddr); break; case AF_INET6: iph6 = ipv6_hdr(skb); audit_log_format(audit_buf, " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x", &iph6->saddr, &iph6->daddr, iph6->flow_lbl[0] & 0x0f, iph6->flow_lbl[1], iph6->flow_lbl[2]); break; } } void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SAD-add"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); xfrm_audit_helper_sainfo(x, audit_buf); audit_log_format(audit_buf, " res=%u", result); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_add); void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SAD-delete"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); xfrm_audit_helper_sainfo(x, audit_buf); audit_log_format(audit_buf, " res=%u", result); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_delete); void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-replay-overflow"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); /* don't record the sequence number because it's inherent in this kind * of audit message */ spi = ntohl(x->id.spi); audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_replay_overflow); void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-replayed-pkt"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); spi = ntohl(x->id.spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_replay); void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SA-notfound"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, family, audit_buf); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound_simple); void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-notfound"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, family, audit_buf); spi = ntohl(net_spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound); void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb, u8 proto) { struct audit_buffer *audit_buf; __be32 net_spi; __be32 net_seq; audit_buf = xfrm_audit_start("SA-icv-failure"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); if (xfrm_parse_spi(skb, proto, &net_spi, &net_seq) == 0) { u32 spi = ntohl(net_spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); } audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_icvfail); #endif /* CONFIG_AUDITSYSCALL */ |
| 3 3 3 3 4 4 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 82 |