1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // SPDX-License-Identifier: GPL-2.0-only /* * linux/arch/x86_64/mm/init.c * * Copyright (C) 1995 Linus Torvalds * Copyright (C) 2000 Pavel Machek <pavel@ucw.cz> * Copyright (C) 2002,2003 Andi Kleen <ak@suse.de> */ #include <linux/signal.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/types.h> #include <linux/ptrace.h> #include <linux/mman.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/initrd.h> #include <linux/pagemap.h> #include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/pci.h> #include <linux/pfn.h> #include <linux/poison.h> #include <linux/dma-mapping.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> #include <linux/memremap.h> #include <linux/nmi.h> #include <linux/gfp.h> #include <linux/kcore.h> #include <asm/processor.h> #include <asm/bios_ebda.h> #include <linux/uaccess.h> #include <asm/pgalloc.h> #include <asm/dma.h> #include <asm/fixmap.h> #include <asm/e820/api.h> #include <asm/apic.h> #include <asm/tlb.h> #include <asm/mmu_context.h> #include <asm/proto.h> #include <asm/smp.h> #include <asm/sections.h> #include <asm/kdebug.h> #include <asm/numa.h> #include <asm/set_memory.h> #include <asm/init.h> #include <asm/uv/uv.h> #include <asm/setup.h> #include <asm/ftrace.h> #include "mm_internal.h" #include "ident_map.c" #define DEFINE_POPULATE(fname, type1, type2, init) \ static inline void fname##_init(struct mm_struct *mm, \ type1##_t *arg1, type2##_t *arg2, bool init) \ { \ if (init) \ fname##_safe(mm, arg1, arg2); \ else \ fname(mm, arg1, arg2); \ } DEFINE_POPULATE(p4d_populate, p4d, pud, init) DEFINE_POPULATE(pgd_populate, pgd, p4d, init) DEFINE_POPULATE(pud_populate, pud, pmd, init) DEFINE_POPULATE(pmd_populate_kernel, pmd, pte, init) #define DEFINE_ENTRY(type1, type2, init) \ static inline void set_##type1##_init(type1##_t *arg1, \ type2##_t arg2, bool init) \ { \ if (init) \ set_##type1##_safe(arg1, arg2); \ else \ set_##type1(arg1, arg2); \ } DEFINE_ENTRY(p4d, p4d, init) DEFINE_ENTRY(pud, pud, init) DEFINE_ENTRY(pmd, pmd, init) DEFINE_ENTRY(pte, pte, init) /* * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the * physical space so we can cache the place of the first one and move * around without checking the pgd every time. */ /* Bits supported by the hardware: */ pteval_t __supported_pte_mask __read_mostly = ~0; /* Bits allowed in normal kernel mappings: */ pteval_t __default_kernel_pte_mask __read_mostly = ~0; EXPORT_SYMBOL_GPL(__supported_pte_mask); /* Used in PAGE_KERNEL_* macros which are reasonably used out-of-tree: */ EXPORT_SYMBOL(__default_kernel_pte_mask); int force_personality32; /* * noexec32=on|off * Control non executable heap for 32bit processes. * To control the stack too use noexec=off * * on PROT_READ does not imply PROT_EXEC for 32-bit processes (default) * off PROT_READ implies PROT_EXEC */ static int __init nonx32_setup(char *str) { if (!strcmp(str, "on")) force_personality32 &= ~READ_IMPLIES_EXEC; else if (!strcmp(str, "off")) force_personality32 |= READ_IMPLIES_EXEC; return 1; } __setup("noexec32=", nonx32_setup); static void sync_global_pgds_l5(unsigned long start, unsigned long end) { unsigned long addr; for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) { const pgd_t *pgd_ref = pgd_offset_k(addr); struct page *page; /* Check for overflow */ if (addr < start) break; if (pgd_none(*pgd_ref)) continue; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; spinlock_t *pgt_lock; pgd = (pgd_t *)page_address(page) + pgd_index(addr); /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); if (!pgd_none(*pgd_ref) && !pgd_none(*pgd)) BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); if (pgd_none(*pgd)) set_pgd(pgd, *pgd_ref); spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); } } static void sync_global_pgds_l4(unsigned long start, unsigned long end) { unsigned long addr; for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) { pgd_t *pgd_ref = pgd_offset_k(addr); const p4d_t *p4d_ref; struct page *page; /* * With folded p4d, pgd_none() is always false, we need to * handle synchonization on p4d level. */ MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref)); p4d_ref = p4d_offset(pgd_ref, addr); if (p4d_none(*p4d_ref)) continue; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; p4d_t *p4d; spinlock_t *pgt_lock; pgd = (pgd_t *)page_address(page) + pgd_index(addr); p4d = p4d_offset(pgd, addr); /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); if (!p4d_none(*p4d_ref) && !p4d_none(*p4d)) BUG_ON(p4d_page_vaddr(*p4d) != p4d_page_vaddr(*p4d_ref)); if (p4d_none(*p4d)) set_p4d(p4d, *p4d_ref); spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); } } /* * When memory was added make sure all the processes MM have * suitable PGD entries in the local PGD level page. */ static void sync_global_pgds(unsigned long start, unsigned long end) { if (pgtable_l5_enabled()) sync_global_pgds_l5(start, end); else sync_global_pgds_l4(start, end); } /* * NOTE: This function is marked __ref because it calls __init function * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0. */ static __ref void *spp_getpage(void) { void *ptr; if (after_bootmem) ptr = (void *) get_zeroed_page(GFP_ATOMIC); else ptr = memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) { panic("set_pte_phys: cannot allocate page data %s\n", after_bootmem ? "after bootmem" : ""); } pr_debug("spp_getpage %p\n", ptr); return ptr; } static p4d_t *fill_p4d(pgd_t *pgd, unsigned long vaddr) { if (pgd_none(*pgd)) { p4d_t *p4d = (p4d_t *)spp_getpage(); pgd_populate(&init_mm, pgd, p4d); if (p4d != p4d_offset(pgd, 0)) printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n", p4d, p4d_offset(pgd, 0)); } return p4d_offset(pgd, vaddr); } static pud_t *fill_pud(p4d_t *p4d, unsigned long vaddr) { if (p4d_none(*p4d)) { pud_t *pud = (pud_t *)spp_getpage(); p4d_populate(&init_mm, p4d, pud); if (pud != pud_offset(p4d, 0)) printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", pud, pud_offset(p4d, 0)); } return pud_offset(p4d, vaddr); } static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr) { if (pud_none(*pud)) { pmd_t *pmd = (pmd_t *) spp_getpage(); pud_populate(&init_mm, pud, pmd); if (pmd != pmd_offset(pud, 0)) printk(KERN_ERR "PAGETABLE BUG #02! %p <-> %p\n", pmd, pmd_offset(pud, 0)); } return pmd_offset(pud, vaddr); } static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr) { if (pmd_none(*pmd)) { pte_t *pte = (pte_t *) spp_getpage(); pmd_populate_kernel(&init_mm, pmd, pte); if (pte != pte_offset_kernel(pmd, 0)) printk(KERN_ERR "PAGETABLE BUG #03!\n"); } return pte_offset_kernel(pmd, vaddr); } static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte) { pmd_t *pmd = fill_pmd(pud, vaddr); pte_t *pte = fill_pte(pmd, vaddr); set_pte(pte, new_pte); /* * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ flush_tlb_one_kernel(vaddr); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte) { p4d_t *p4d = p4d_page + p4d_index(vaddr); pud_t *pud = fill_pud(p4d, vaddr); __set_pte_vaddr(pud, vaddr, new_pte); } void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) { pud_t *pud = pud_page + pud_index(vaddr); __set_pte_vaddr(pud, vaddr, new_pte); } void set_pte_vaddr(unsigned long vaddr, pte_t pteval) { pgd_t *pgd; p4d_t *p4d_page; pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval)); pgd = pgd_offset_k(vaddr); if (pgd_none(*pgd)) { printk(KERN_ERR "PGD FIXMAP MISSING, it should be setup in head.S!\n"); return; } p4d_page = p4d_offset(pgd, 0); set_pte_vaddr_p4d(p4d_page, vaddr, pteval); } pmd_t * __init populate_extra_pmd(unsigned long vaddr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pgd = pgd_offset_k(vaddr); p4d = fill_p4d(pgd, vaddr); pud = fill_pud(p4d, vaddr); return fill_pmd(pud, vaddr); } pte_t * __init populate_extra_pte(unsigned long vaddr) { pmd_t *pmd; pmd = populate_extra_pmd(vaddr); return fill_pte(pmd, vaddr); } /* * Create large page table mappings for a range of physical addresses. */ static void __init __init_extra_mapping(unsigned long phys, unsigned long size, enum page_cache_mode cache) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgprot_t prot; pgprot_val(prot) = pgprot_val(PAGE_KERNEL_LARGE) | protval_4k_2_large(cachemode2protval(cache)); BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK)); for (; size; phys += PMD_SIZE, size -= PMD_SIZE) { pgd = pgd_offset_k((unsigned long)__va(phys)); if (pgd_none(*pgd)) { p4d = (p4d_t *) spp_getpage(); set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE | _PAGE_USER)); } p4d = p4d_offset(pgd, (unsigned long)__va(phys)); if (p4d_none(*p4d)) { pud = (pud_t *) spp_getpage(); set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE | _PAGE_USER)); } pud = pud_offset(p4d, (unsigned long)__va(phys)); if (pud_none(*pud)) { pmd = (pmd_t *) spp_getpage(); set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER)); } pmd = pmd_offset(pud, phys); BUG_ON(!pmd_none(*pmd)); set_pmd(pmd, __pmd(phys | pgprot_val(prot))); } } void __init init_extra_mapping_wb(unsigned long phys, unsigned long size) { __init_extra_mapping(phys, size, _PAGE_CACHE_MODE_WB); } void __init init_extra_mapping_uc(unsigned long phys, unsigned long size) { __init_extra_mapping(phys, size, _PAGE_CACHE_MODE_UC); } /* * The head.S code sets up the kernel high mapping: * * from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text) * * phys_base holds the negative offset to the kernel, which is added * to the compile time generated pmds. This results in invalid pmds up * to the point where we hit the physaddr 0 mapping. * * We limit the mappings to the region from _text to _brk_end. _brk_end * is rounded up to the 2MB boundary. This catches the invalid pmds as * well, as they are located before _text: */ void __init cleanup_highmap(void) { unsigned long vaddr = __START_KERNEL_map; unsigned long vaddr_end = __START_KERNEL_map + KERNEL_IMAGE_SIZE; unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1; pmd_t *pmd = level2_kernel_pgt; /* * Native path, max_pfn_mapped is not set yet. * Xen has valid max_pfn_mapped set in * arch/x86/xen/mmu.c:xen_setup_kernel_pagetable(). */ if (max_pfn_mapped) vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT); for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) { if (pmd_none(*pmd)) continue; if (vaddr < (unsigned long) _text || vaddr > end) set_pmd(pmd, __pmd(0)); } } /* * Create PTE level page table mapping for physical addresses. * It returns the last physical address mapped. */ static unsigned long __meminit phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end, pgprot_t prot, bool init) { unsigned long pages = 0, paddr_next; unsigned long paddr_last = paddr_end; pte_t *pte; int i; pte = pte_page + pte_index(paddr); i = pte_index(paddr); for (; i < PTRS_PER_PTE; i++, paddr = paddr_next, pte++) { paddr_next = (paddr & PAGE_MASK) + PAGE_SIZE; if (paddr >= paddr_end) { if (!after_bootmem && !e820__mapped_any(paddr & PAGE_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PAGE_MASK, paddr_next, E820_TYPE_RESERVED_KERN)) set_pte_init(pte, __pte(0), init); continue; } /* * We will re-use the existing mapping. * Xen for example has some special requirements, like mapping * pagetable pages as RO. So assume someone who pre-setup * these mappings are more intelligent. */ if (!pte_none(*pte)) { if (!after_bootmem) pages++; continue; } if (0) pr_info(" pte=%p addr=%lx pte=%016lx\n", pte, paddr, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL).pte); pages++; set_pte_init(pte, pfn_pte(paddr >> PAGE_SHIFT, prot), init); paddr_last = (paddr & PAGE_MASK) + PAGE_SIZE; } update_page_count(PG_LEVEL_4K, pages); return paddr_last; } /* * Create PMD level page table mapping for physical addresses. The virtual * and physical address have to be aligned at this level. * It returns the last physical address mapped. */ static unsigned long __meminit phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t prot, bool init) { unsigned long pages = 0, paddr_next; unsigned long paddr_last = paddr_end; int i = pmd_index(paddr); for (; i < PTRS_PER_PMD; i++, paddr = paddr_next) { pmd_t *pmd = pmd_page + pmd_index(paddr); pte_t *pte; pgprot_t new_prot = prot; paddr_next = (paddr & PMD_MASK) + PMD_SIZE; if (paddr >= paddr_end) { if (!after_bootmem && !e820__mapped_any(paddr & PMD_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PMD_MASK, paddr_next, E820_TYPE_RESERVED_KERN)) set_pmd_init(pmd, __pmd(0), init); continue; } if (!pmd_none(*pmd)) { if (!pmd_large(*pmd)) { spin_lock(&init_mm.page_table_lock); pte = (pte_t *)pmd_page_vaddr(*pmd); paddr_last = phys_pte_init(pte, paddr, paddr_end, prot, init); spin_unlock(&init_mm.page_table_lock); continue; } /* * If we are ok with PG_LEVEL_2M mapping, then we will * use the existing mapping, * * Otherwise, we will split the large page mapping but * use the same existing protection bits except for * large page, so that we don't violate Intel's TLB * Application note (317080) which says, while changing * the page sizes, new and old translations should * not differ with respect to page frame and * attributes. */ if (page_size_mask & (1 << PG_LEVEL_2M)) { if (!after_bootmem) pages++; paddr_last = paddr_next; continue; } new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd)); } if (page_size_mask & (1<<PG_LEVEL_2M)) { pages++; spin_lock(&init_mm.page_table_lock); set_pte_init((pte_t *)pmd, pfn_pte((paddr & PMD_MASK) >> PAGE_SHIFT, __pgprot(pgprot_val(prot) | _PAGE_PSE)), init); spin_unlock(&init_mm.page_table_lock); paddr_last = paddr_next; continue; } pte = alloc_low_page(); paddr_last = phys_pte_init(pte, paddr, paddr_end, new_prot, init); spin_lock(&init_mm.page_table_lock); pmd_populate_kernel_init(&init_mm, pmd, pte, init); spin_unlock(&init_mm.page_table_lock); } update_page_count(PG_LEVEL_2M, pages); return paddr_last; } /* * Create PUD level page table mapping for physical addresses. The virtual * and physical address do not have to be aligned at this level. KASLR can * randomize virtual addresses up to this level. * It returns the last physical address mapped. */ static unsigned long __meminit phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t _prot, bool init) { unsigned long pages = 0, paddr_next; unsigned long paddr_last = paddr_end; unsigned long vaddr = (unsigned long)__va(paddr); int i = pud_index(vaddr); for (; i < PTRS_PER_PUD; i++, paddr = paddr_next) { pud_t *pud; pmd_t *pmd; pgprot_t prot = _prot; vaddr = (unsigned long)__va(paddr); pud = pud_page + pud_index(vaddr); paddr_next = (paddr & PUD_MASK) + PUD_SIZE; if (paddr >= paddr_end) { if (!after_bootmem && !e820__mapped_any(paddr & PUD_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & PUD_MASK, paddr_next, E820_TYPE_RESERVED_KERN)) set_pud_init(pud, __pud(0), init); continue; } if (!pud_none(*pud)) { if (!pud_large(*pud)) { pmd = pmd_offset(pud, 0); paddr_last = phys_pmd_init(pmd, paddr, paddr_end, page_size_mask, prot, init); continue; } /* * If we are ok with PG_LEVEL_1G mapping, then we will * use the existing mapping. * * Otherwise, we will split the gbpage mapping but use * the same existing protection bits except for large * page, so that we don't violate Intel's TLB * Application note (317080) which says, while changing * the page sizes, new and old translations should * not differ with respect to page frame and * attributes. */ if (page_size_mask & (1 << PG_LEVEL_1G)) { if (!after_bootmem) pages++; paddr_last = paddr_next; continue; } prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud)); } if (page_size_mask & (1<<PG_LEVEL_1G)) { pages++; spin_lock(&init_mm.page_table_lock); prot = __pgprot(pgprot_val(prot) | __PAGE_KERNEL_LARGE); set_pte_init((pte_t *)pud, pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT, prot), init); spin_unlock(&init_mm.page_table_lock); paddr_last = paddr_next; continue; } pmd = alloc_low_page(); paddr_last = phys_pmd_init(pmd, paddr, paddr_end, page_size_mask, prot, init); spin_lock(&init_mm.page_table_lock); pud_populate_init(&init_mm, pud, pmd, init); spin_unlock(&init_mm.page_table_lock); } update_page_count(PG_LEVEL_1G, pages); return paddr_last; } static unsigned long __meminit phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t prot, bool init) { unsigned long vaddr, vaddr_end, vaddr_next, paddr_next, paddr_last; paddr_last = paddr_end; vaddr = (unsigned long)__va(paddr); vaddr_end = (unsigned long)__va(paddr_end); if (!pgtable_l5_enabled()) return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask, prot, init); for (; vaddr < vaddr_end; vaddr = vaddr_next) { p4d_t *p4d = p4d_page + p4d_index(vaddr); pud_t *pud; vaddr_next = (vaddr & P4D_MASK) + P4D_SIZE; paddr = __pa(vaddr); if (paddr >= paddr_end) { paddr_next = __pa(vaddr_next); if (!after_bootmem && !e820__mapped_any(paddr & P4D_MASK, paddr_next, E820_TYPE_RAM) && !e820__mapped_any(paddr & P4D_MASK, paddr_next, E820_TYPE_RESERVED_KERN)) set_p4d_init(p4d, __p4d(0), init); continue; } if (!p4d_none(*p4d)) { pud = pud_offset(p4d, 0); paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end), page_size_mask, prot, init); continue; } pud = alloc_low_page(); paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end), page_size_mask, prot, init); spin_lock(&init_mm.page_table_lock); p4d_populate_init(&init_mm, p4d, pud, init); spin_unlock(&init_mm.page_table_lock); } return paddr_last; } static unsigned long __meminit __kernel_physical_mapping_init(unsigned long paddr_start, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t prot, bool init) { bool pgd_changed = false; unsigned long vaddr, vaddr_start, vaddr_end, vaddr_next, paddr_last; paddr_last = paddr_end; vaddr = (unsigned long)__va(paddr_start); vaddr_end = (unsigned long)__va(paddr_end); vaddr_start = vaddr; for (; vaddr < vaddr_end; vaddr = vaddr_next) { pgd_t *pgd = pgd_offset_k(vaddr); p4d_t *p4d; vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE; if (pgd_val(*pgd)) { p4d = (p4d_t *)pgd_page_vaddr(*pgd); paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask, prot, init); continue; } p4d = alloc_low_page(); paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask, prot, init); spin_lock(&init_mm.page_table_lock); if (pgtable_l5_enabled()) pgd_populate_init(&init_mm, pgd, p4d, init); else p4d_populate_init(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d, init); spin_unlock(&init_mm.page_table_lock); pgd_changed = true; } if (pgd_changed) sync_global_pgds(vaddr_start, vaddr_end - 1); return paddr_last; } /* * Create page table mapping for the physical memory for specific physical * addresses. Note that it can only be used to populate non-present entries. * The virtual and physical addresses have to be aligned on PMD level * down. It returns the last physical address mapped. */ unsigned long __meminit kernel_physical_mapping_init(unsigned long paddr_start, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t prot) { return __kernel_physical_mapping_init(paddr_start, paddr_end, page_size_mask, prot, true); } /* * This function is similar to kernel_physical_mapping_init() above with the * exception that it uses set_{pud,pmd}() instead of the set_{pud,pte}_safe() * when updating the mapping. The caller is responsible to flush the TLBs after * the function returns. */ unsigned long __meminit kernel_physical_mapping_change(unsigned long paddr_start, unsigned long paddr_end, unsigned long page_size_mask) { return __kernel_physical_mapping_init(paddr_start, paddr_end, page_size_mask, PAGE_KERNEL, false); } #ifndef CONFIG_NUMA void __init initmem_init(void) { memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); } #endif void __init paging_init(void) { sparse_init(); /* * clear the default setting with node 0 * note: don't use nodes_clear here, that is really clearing when * numa support is not compiled in, and later node_set_state * will not set it back. */ node_clear_state(0, N_MEMORY); node_clear_state(0, N_NORMAL_MEMORY); zone_sizes_init(); } /* * Memory hotplug specific functions */ #ifdef CONFIG_MEMORY_HOTPLUG /* * After memory hotplug the variables max_pfn, max_low_pfn and high_memory need * updating. */ static void update_end_of_memory_vars(u64 start, u64 size) { unsigned long end_pfn = PFN_UP(start + size); if (end_pfn > max_pfn) { max_pfn = end_pfn; max_low_pfn = end_pfn; high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; } } int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params) { int ret; ret = __add_pages(nid, start_pfn, nr_pages, params); WARN_ON_ONCE(ret); /* update max_pfn, max_low_pfn and high_memory */ update_end_of_memory_vars(start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT); return ret; } int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; init_memory_mapping(start, start + size, params->pgprot); return add_pages(nid, start_pfn, nr_pages, params); } #define PAGE_INUSE 0xFD static void __meminit free_pagetable(struct page *page, int order) { unsigned long magic; unsigned int nr_pages = 1 << order; /* bootmem page has reserved flag */ if (PageReserved(page)) { __ClearPageReserved(page); magic = (unsigned long)page->freelist; if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) { while (nr_pages--) put_page_bootmem(page++); } else while (nr_pages--) free_reserved_page(page++); } else free_pages((unsigned long)page_address(page), order); } static void __meminit free_hugepage_table(struct page *page, struct vmem_altmap *altmap) { if (altmap) vmem_altmap_free(altmap, PMD_SIZE / PAGE_SIZE); else free_pagetable(page, get_order(PMD_SIZE)); } static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) { pte_t *pte; int i; for (i = 0; i < PTRS_PER_PTE; i++) { pte = pte_start + i; if (!pte_none(*pte)) return; } /* free a pte talbe */ free_pagetable(pmd_page(*pmd), 0); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); } static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) { pmd_t *pmd; int i; for (i = 0; i < PTRS_PER_PMD; i++) { pmd = pmd_start + i; if (!pmd_none(*pmd)) return; } /* free a pmd talbe */ free_pagetable(pud_page(*pud), 0); spin_lock(&init_mm.page_table_lock); pud_clear(pud); spin_unlock(&init_mm.page_table_lock); } static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) { pud_t *pud; int i; for (i = 0; i < PTRS_PER_PUD; i++) { pud = pud_start + i; if (!pud_none(*pud)) return; } /* free a pud talbe */ free_pagetable(p4d_page(*p4d), 0); spin_lock(&init_mm.page_table_lock); p4d_clear(p4d); spin_unlock(&init_mm.page_table_lock); } static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, bool direct) { unsigned long next, pages = 0; pte_t *pte; void *page_addr; phys_addr_t phys_addr; pte = pte_start + pte_index(addr); for (; addr < end; addr = next, pte++) { next = (addr + PAGE_SIZE) & PAGE_MASK; if (next > end) next = end; if (!pte_present(*pte)) continue; /* * We mapped [0,1G) memory as identity mapping when * initializing, in arch/x86/kernel/head_64.S. These * pagetables cannot be removed. */ phys_addr = pte_val(*pte) + (addr & PAGE_MASK); if (phys_addr < (phys_addr_t)0x40000000) return; if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) { /* * Do not free direct mapping pages since they were * freed when offlining, or simplely not in use. */ if (!direct) free_pagetable(pte_page(*pte), 0); spin_lock(&init_mm.page_table_lock); pte_clear(&init_mm, addr, pte); spin_unlock(&init_mm.page_table_lock); /* For non-direct mapping, pages means nothing. */ pages++; } else { /* * If we are here, we are freeing vmemmap pages since * direct mapped memory ranges to be freed are aligned. * * If we are not removing the whole page, it means * other page structs in this page are being used and * we canot remove them. So fill the unused page_structs * with 0xFD, and remove the page when it is wholly * filled with 0xFD. */ memset((void *)addr, PAGE_INUSE, next - addr); page_addr = page_address(pte_page(*pte)); if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) { free_pagetable(pte_page(*pte), 0); spin_lock(&init_mm.page_table_lock); pte_clear(&init_mm, addr, pte); spin_unlock(&init_mm.page_table_lock); } } } /* Call free_pte_table() in remove_pmd_table(). */ flush_tlb_all(); if (direct) update_page_count(PG_LEVEL_4K, -pages); } static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, bool direct, struct vmem_altmap *altmap) { unsigned long next, pages = 0; pte_t *pte_base; pmd_t *pmd; void *page_addr; pmd = pmd_start + pmd_index(addr); for (; addr < end; addr = next, pmd++) { next = pmd_addr_end(addr, end); if (!pmd_present(*pmd)) continue; if (pmd_large(*pmd)) { if (IS_ALIGNED(addr, PMD_SIZE) && IS_ALIGNED(next, PMD_SIZE)) { if (!direct) free_hugepage_table(pmd_page(*pmd), altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); pages++; } else { /* If here, we are freeing vmemmap pages. */ memset((void *)addr, PAGE_INUSE, next - addr); page_addr = page_address(pmd_page(*pmd)); if (!memchr_inv(page_addr, PAGE_INUSE, PMD_SIZE)) { free_hugepage_table(pmd_page(*pmd), altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); } } continue; } pte_base = (pte_t *)pmd_page_vaddr(*pmd); remove_pte_table(pte_base, addr, next, direct); free_pte_table(pte_base, pmd); } /* Call free_pmd_table() in remove_pud_table(). */ if (direct) update_page_count(PG_LEVEL_2M, -pages); } static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, struct vmem_altmap *altmap, bool direct) { unsigned long next, pages = 0; pmd_t *pmd_base; pud_t *pud; void *page_addr; pud = pud_start + pud_index(addr); for (; addr < end; addr = next, pud++) { next = pud_addr_end(addr, end); if (!pud_present(*pud)) continue; if (pud_large(*pud)) { if (IS_ALIGNED(addr, PUD_SIZE) && IS_ALIGNED(next, PUD_SIZE)) { if (!direct) free_pagetable(pud_page(*pud), get_order(PUD_SIZE)); spin_lock(&init_mm.page_table_lock); pud_clear(pud); spin_unlock(&init_mm.page_table_lock); pages++; } else { /* If here, we are freeing vmemmap pages. */ memset((void *)addr, PAGE_INUSE, next - addr); page_addr = page_address(pud_page(*pud)); if (!memchr_inv(page_addr, PAGE_INUSE, PUD_SIZE)) { free_pagetable(pud_page(*pud), get_order(PUD_SIZE)); spin_lock(&init_mm.page_table_lock); pud_clear(pud); spin_unlock(&init_mm.page_table_lock); } } continue; } pmd_base = pmd_offset(pud, 0); remove_pmd_table(pmd_base, addr, next, direct, altmap); free_pmd_table(pmd_base, pud); } if (direct) update_page_count(PG_LEVEL_1G, -pages); } static void __meminit remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, struct vmem_altmap *altmap, bool direct) { unsigned long next, pages = 0; pud_t *pud_base; p4d_t *p4d; p4d = p4d_start + p4d_index(addr); for (; addr < end; addr = next, p4d++) { next = p4d_addr_end(addr, end); if (!p4d_present(*p4d)) continue; BUILD_BUG_ON(p4d_large(*p4d)); pud_base = pud_offset(p4d, 0); remove_pud_table(pud_base, addr, next, altmap, direct); /* * For 4-level page tables we do not want to free PUDs, but in the * 5-level case we should free them. This code will have to change * to adapt for boot-time switching between 4 and 5 level page tables. */ if (pgtable_l5_enabled()) free_pud_table(pud_base, p4d); } if (direct) update_page_count(PG_LEVEL_512G, -pages); } /* start and end are both virtual address. */ static void __meminit remove_pagetable(unsigned long start, unsigned long end, bool direct, struct vmem_altmap *altmap) { unsigned long next; unsigned long addr; pgd_t *pgd; p4d_t *p4d; for (addr = start; addr < end; addr = next) { next = pgd_addr_end(addr, end); pgd = pgd_offset_k(addr); if (!pgd_present(*pgd)) continue; p4d = p4d_offset(pgd, 0); remove_p4d_table(p4d, addr, next, altmap, direct); } flush_tlb_all(); } void __ref vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) { remove_pagetable(start, end, false, altmap); } static void __meminit kernel_physical_mapping_remove(unsigned long start, unsigned long end) { start = (unsigned long)__va(start); end = (unsigned long)__va(end); remove_pagetable(start, end, true, NULL); } void __ref arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; __remove_pages(start_pfn, nr_pages, altmap); kernel_physical_mapping_remove(start, start + size); } #endif /* CONFIG_MEMORY_HOTPLUG */ static struct kcore_list kcore_vsyscall; static void __init register_page_bootmem_info(void) { #ifdef CONFIG_NUMA int i; for_each_online_node(i) register_page_bootmem_info_node(NODE_DATA(i)); #endif } /* * Pre-allocates page-table pages for the vmalloc area in the kernel page-table. * Only the level which needs to be synchronized between all page-tables is * allocated because the synchronization can be expensive. */ static void __init preallocate_vmalloc_pages(void) { unsigned long addr; const char *lvl; for (addr = VMALLOC_START; addr <= VMALLOC_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) { pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; lvl = "p4d"; p4d = p4d_alloc(&init_mm, pgd, addr); if (!p4d) goto failed; if (pgtable_l5_enabled()) continue; /* * The goal here is to allocate all possibly required * hardware page tables pointed to by the top hardware * level. * * On 4-level systems, the P4D layer is folded away and * the above code does no preallocation. Below, go down * to the pud _software_ level to ensure the second * hardware level is allocated on 4-level systems too. */ lvl = "pud"; pud = pud_alloc(&init_mm, p4d, addr); if (!pud) goto failed; } return; failed: /* * The pages have to be there now or they will be missing in * process page-tables later. */ panic("Failed to pre-allocate %s pages for vmalloc area\n", lvl); } void __init mem_init(void) { pci_iommu_alloc(); /* clear_bss() already clear the empty_zero_page */ /* this will put all memory onto the freelists */ memblock_free_all(); after_bootmem = 1; x86_init.hyper.init_after_bootmem(); /* * Must be done after boot memory is put on freelist, because here we * might set fields in deferred struct pages that have not yet been * initialized, and memblock_free_all() initializes all the reserved * deferred pages for us. */ register_page_bootmem_info(); /* Register memory areas for /proc/kcore */ if (get_gate_vma(&init_mm)) kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER); preallocate_vmalloc_pages(); mem_init_print_info(NULL); } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask) { /* * More CPUs always led to greater speedups on tested systems, up to * all the nodes' CPUs. Use all since the system is otherwise idle * now. */ return max_t(int, cpumask_weight(node_cpumask), 1); } #endif int kernel_set_to_readonly; void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); unsigned long rodata_start = PFN_ALIGN(__start_rodata); unsigned long end = (unsigned long)__end_rodata_hpage_align; unsigned long text_end = PFN_ALIGN(_etext); unsigned long rodata_end = PFN_ALIGN(__end_rodata); unsigned long all_end; printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); kernel_set_to_readonly = 1; /* * The rodata/data/bss/brk section (but not the kernel text!) * should also be not-executable. * * We align all_end to PMD_SIZE because the existing mapping * is a full PMD. If we would align _brk_end to PAGE_SIZE we * split the PMD and the reminder between _brk_end and the end * of the PMD will remain mapped executable. * * Any PMD which was setup after the one which covers _brk_end * has been zapped already via cleanup_highmem(). */ all_end = roundup((unsigned long)_brk_end, PMD_SIZE); set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); set_ftrace_ops_ro(); #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end); set_memory_rw(start, (end-start) >> PAGE_SHIFT); printk(KERN_INFO "Testing CPA: again\n"); set_memory_ro(start, (end-start) >> PAGE_SHIFT); #endif free_kernel_image_pages("unused kernel image (text/rodata gap)", (void *)text_end, (void *)rodata_start); free_kernel_image_pages("unused kernel image (rodata/data gap)", (void *)rodata_end, (void *)_sdata); debug_checkwx(); } int kern_addr_valid(unsigned long addr) { unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; if (above != 0 && above != -1UL) return 0; pgd = pgd_offset_k(addr); if (pgd_none(*pgd)) return 0; p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return 0; pud = pud_offset(p4d, addr); if (!pud_present(*pud)) return 0; if (pud_large(*pud)) return pfn_valid(pud_pfn(*pud)); pmd = pmd_offset(pud, addr); if (!pmd_present(*pmd)) return 0; if (pmd_large(*pmd)) return pfn_valid(pmd_pfn(*pmd)); pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) return 0; return pfn_valid(pte_pfn(*pte)); } /* * Block size is the minimum amount of memory which can be hotplugged or * hotremoved. It must be power of two and must be equal or larger than * MIN_MEMORY_BLOCK_SIZE. */ #define MAX_BLOCK_SIZE (2UL << 30) /* Amount of ram needed to start using large blocks */ #define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30) /* Adjustable memory block size */ static unsigned long set_memory_block_size; int __init set_memory_block_size_order(unsigned int order) { unsigned long size = 1UL << order; if (size > MEM_SIZE_FOR_LARGE_BLOCK || size < MIN_MEMORY_BLOCK_SIZE) return -EINVAL; set_memory_block_size = size; return 0; } static unsigned long probe_memory_block_size(void) { unsigned long boot_mem_end = max_pfn << PAGE_SHIFT; unsigned long bz; /* If memory block size has been set, then use it */ bz = set_memory_block_size; if (bz) goto done; /* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */ if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) { bz = MIN_MEMORY_BLOCK_SIZE; goto done; } /* * Use max block size to minimize overhead on bare metal, where * alignment for memory hotplug isn't a concern. */ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) { bz = MAX_BLOCK_SIZE; goto done; } /* Find the largest allowed block size that aligns to memory end */ for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) { if (IS_ALIGNED(boot_mem_end, bz)) break; } done: pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20); return bz; } static unsigned long memory_block_size_probed; unsigned long memory_block_size_bytes(void) { if (!memory_block_size_probed) memory_block_size_probed = probe_memory_block_size(); return memory_block_size_probed; } #ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Initialise the sparsemem vmemmap using huge-pages at the PMD level. */ static long __meminitdata addr_start, addr_end; static void __meminitdata *p_start, *p_end; static int __meminitdata node_start; static int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { unsigned long addr; unsigned long next; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; for (addr = start; addr < end; addr = next) { next = pmd_addr_end(addr, end); pgd = vmemmap_pgd_populate(addr, node); if (!pgd) return -ENOMEM; p4d = vmemmap_p4d_populate(pgd, addr, node); if (!p4d) return -ENOMEM; pud = vmemmap_pud_populate(p4d, addr, node); if (!pud) return -ENOMEM; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { void *p; p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); if (p) { pte_t entry; entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL_LARGE); set_pmd(pmd, __pmd(pte_val(entry))); /* check to see if we have contiguous blocks */ if (p_end != p || node_start != node) { if (p_start) pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", addr_start, addr_end-1, p_start, p_end-1, node_start); addr_start = addr; node_start = node; p_start = p; } addr_end = addr + PMD_SIZE; p_end = p + PMD_SIZE; continue; } else if (altmap) return -ENOMEM; /* no fallback */ } else if (pmd_large(*pmd)) { vmemmap_verify((pte_t *)pmd, node, addr, next); continue; } if (vmemmap_populate_basepages(addr, next, node, NULL)) return -ENOMEM; } return 0; } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { int err; if (end - start < PAGES_PER_SECTION * sizeof(struct page)) err = vmemmap_populate_basepages(start, end, node, NULL); else if (boot_cpu_has(X86_FEATURE_PSE)) err = vmemmap_populate_hugepages(start, end, node, altmap); else if (altmap) { pr_err_once("%s: no cpu support for altmap allocations\n", __func__); err = -ENOMEM; } else err = vmemmap_populate_basepages(start, end, node, NULL); if (!err) sync_global_pgds(start, end - 1); return err; } #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE) void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long nr_pages) { unsigned long addr = (unsigned long)start_page; unsigned long end = (unsigned long)(start_page + nr_pages); unsigned long next; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; unsigned int nr_pmd_pages; struct page *page; for (; addr < end; addr = next) { pte_t *pte = NULL; pgd = pgd_offset_k(addr); if (pgd_none(*pgd)) { next = (addr + PAGE_SIZE) & PAGE_MASK; continue; } get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO); p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { next = (addr + PAGE_SIZE) & PAGE_MASK; continue; } get_page_bootmem(section_nr, p4d_page(*p4d), MIX_SECTION_INFO); pud = pud_offset(p4d, addr); if (pud_none(*pud)) { next = (addr + PAGE_SIZE) & PAGE_MASK; continue; } get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO); if (!boot_cpu_has(X86_FEATURE_PSE)) { next = (addr + PAGE_SIZE) & PAGE_MASK; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) continue; get_page_bootmem(section_nr, pmd_page(*pmd), MIX_SECTION_INFO); pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) continue; get_page_bootmem(section_nr, pte_page(*pte), SECTION_INFO); } else { next = pmd_addr_end(addr, end); pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) continue; nr_pmd_pages = 1 << get_order(PMD_SIZE); page = pmd_page(*pmd); while (nr_pmd_pages--) get_page_bootmem(section_nr, page++, SECTION_INFO); } } } #endif void __meminit vmemmap_populate_print_last(void) { if (p_start) { pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", addr_start, addr_end-1, p_start, p_end-1, node_start); p_start = NULL; p_end = NULL; node_start = 0; } } #endif
26 23 23 23 23 23 23 22 22 5 12 12 12 12 11 16 6 6 20 12 12 28 27 26 22 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 // SPDX-License-Identifier: GPL-2.0-only #include <linux/fs.h> #include <linux/fs_struct.h> #include <linux/kernel_read_file.h> #include <linux/security.h> #include <linux/vmalloc.h> /** * kernel_read_file() - read file contents into a kernel buffer * * @file file to read from * @offset where to start reading from (see below). * @buf pointer to a "void *" buffer for reading into (if * *@buf is NULL, a buffer will be allocated, and * @buf_size will be ignored) * @buf_size size of buf, if already allocated. If @buf not * allocated, this is the largest size to allocate. * @file_size if non-NULL, the full size of @file will be * written here. * @id the kernel_read_file_id identifying the type of * file contents being read (for LSMs to examine) * * @offset must be 0 unless both @buf and @file_size are non-NULL * (i.e. the caller must be expecting to read partial file contents * via an already-allocated @buf, in at most @buf_size chunks, and * will be able to determine when the entire file was read by * checking @file_size). This isn't a recommended way to read a * file, though, since it is possible that the contents might * change between calls to kernel_read_file(). * * Returns number of bytes read (no single read will be bigger * than INT_MAX), or negative on error. * */ int kernel_read_file(struct file *file, loff_t offset, void **buf, size_t buf_size, size_t *file_size, enum kernel_read_file_id id) { loff_t i_size, pos; size_t copied; void *allocated = NULL; bool whole_file; int ret; if (offset != 0 && (!*buf || !file_size)) return -EINVAL; if (!S_ISREG(file_inode(file)->i_mode)) return -EINVAL; ret = deny_write_access(file); if (ret) return ret; i_size = i_size_read(file_inode(file)); if (i_size <= 0) { ret = -EINVAL; goto out; } /* The file is too big for sane activities. */ if (i_size > INT_MAX) { ret = -EFBIG; goto out; } /* The entire file cannot be read in one buffer. */ if (!file_size && offset == 0 && i_size > buf_size) { ret = -EFBIG; goto out; } whole_file = (offset == 0 && i_size <= buf_size); ret = security_kernel_read_file(file, id, whole_file); if (ret) goto out; if (file_size) *file_size = i_size; if (!*buf) *buf = allocated = vmalloc(i_size); if (!*buf) { ret = -ENOMEM; goto out; } pos = offset; copied = 0; while (copied < buf_size) { ssize_t bytes; size_t wanted = min_t(size_t, buf_size - copied, i_size - pos); bytes = kernel_read(file, *buf + copied, wanted, &pos); if (bytes < 0) { ret = bytes; goto out_free; } if (bytes == 0) break; copied += bytes; } if (whole_file) { if (pos != i_size) { ret = -EIO; goto out_free; } ret = security_kernel_post_read_file(file, *buf, i_size, id); } out_free: if (ret < 0) { if (allocated) { vfree(*buf); *buf = NULL; } } out: allow_write_access(file); return ret == 0 ? copied : ret; } EXPORT_SYMBOL_GPL(kernel_read_file); int kernel_read_file_from_path(const char *path, loff_t offset, void **buf, size_t buf_size, size_t *file_size, enum kernel_read_file_id id) { struct file *file; int ret; if (!path || !*path) return -EINVAL; file = filp_open(path, O_RDONLY, 0); if (IS_ERR(file)) return PTR_ERR(file); ret = kernel_read_file(file, offset, buf, buf_size, file_size, id); fput(file); return ret; } EXPORT_SYMBOL_GPL(kernel_read_file_from_path); int kernel_read_file_from_path_initns(const char *path, loff_t offset, void **buf, size_t buf_size, size_t *file_size, enum kernel_read_file_id id) { struct file *file; struct path root; int ret; if (!path || !*path) return -EINVAL; task_lock(&init_task); get_fs_root(init_task.fs, &root); task_unlock(&init_task); file = file_open_root(root.dentry, root.mnt, path, O_RDONLY, 0); path_put(&root); if (IS_ERR(file)) return PTR_ERR(file); ret = kernel_read_file(file, offset, buf, buf_size, file_size, id); fput(file); return ret; } EXPORT_SYMBOL_GPL(kernel_read_file_from_path_initns); int kernel_read_file_from_fd(int fd, loff_t offset, void **buf, size_t buf_size, size_t *file_size, enum kernel_read_file_id id) { struct fd f = fdget(fd); int ret = -EBADF; if (!f.file || !(f.file->f_mode & FMODE_READ)) goto out; ret = kernel_read_file(f.file, offset, buf, buf_size, file_size, id); out: fdput(f); return ret; } EXPORT_SYMBOL_GPL(kernel_read_file_from_fd);
2 2 5 96 93 93 130 130 3 3 3 2 130 1 1 1 1 92 92 86 33 93 93 7 5 5 92 93 10 10 9 6 4 4 3 8 795 372 125 5 5 120 114 5 118 7 125 342 87 86 85 1 128 3 3 2 2 2 1 1 129 128 4 3 124 125 3 133 133 133 133 133 88 87 88 87 87 82 6 80 80 86 86 86 85 5 85 85 85 85 85 61 61 61 61 61 131 373 373 373 372 373 372 372 371 30 30 30 372 371 371 372 670 669 669 465 341 45 45 43 37 8 36 8 39 39 4 34 33 12 44 11 11 4 7 1 1 1 7 7 7 4 4 4 10 36 7 7 6 3 3 2 1 7 6 4 2 1 1 2 17 17 5 17 796 43 1 9 11 10 7 37 12 660 660 661 660 661 710 368 37 37 337 1 688 319 319 318 319 319 31 31 24 7 31 31 31 31 31 31 31 23 8 5 5 63 12 5 63 40 70 3 3 3 3 71 71 25 21 41 39 38 38 7 63 63 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 /* * linux/drivers/block/loop.c * * Written by Theodore Ts'o, 3/29/93 * * Copyright 1993 by Theodore Ts'o. Redistribution of this file is * permitted under the GNU General Public License. * * DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993 * more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1996 * * Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994 * Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996 * * Fixed do_loop_request() re-entrancy - Vincent.Renardias@waw.com Mar 20, 1997 * * Added devfs support - Richard Gooch <rgooch@atnf.csiro.au> 16-Jan-1998 * * Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998 * * Loadable modules and other fixes by AK, 1998 * * Make real block number available to downstream transfer functions, enables * CBC (and relatives) mode encryption requiring unique IVs per data block. * Reed H. Petty, rhp@draper.net * * Maximum number of loop devices now dynamic via max_loop module parameter. * Russell Kroll <rkroll@exploits.org> 19990701 * * Maximum number of loop devices when compiled-in now selectable by passing * max_loop=<1-255> to the kernel on boot. * Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999 * * Completely rewrite request handling to be make_request_fn style and * non blocking, pushing work to a helper thread. Lots of fixes from * Al Viro too. * Jens Axboe <axboe@suse.de>, Nov 2000 * * Support up to 256 loop devices * Heinz Mauelshagen <mge@sistina.com>, Feb 2002 * * Support for falling back on the write file operation when the address space * operations write_begin is not available on the backing filesystem. * Anton Altaparmakov, 16 Feb 2005 * * Still To Fix: * - Advisory locking is ignored here. * - Should use an own CAP_* category instead of CAP_SYS_ADMIN * */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/stat.h> #include <linux/errno.h> #include <linux/major.h> #include <linux/wait.h> #include <linux/blkdev.h> #include <linux/blkpg.h> #include <linux/init.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/suspend.h> #include <linux/freezer.h> #include <linux/mutex.h> #include <linux/writeback.h> #include <linux/completion.h> #include <linux/highmem.h> #include <linux/kthread.h> #include <linux/splice.h> #include <linux/sysfs.h> #include <linux/miscdevice.h> #include <linux/falloc.h> #include <linux/uio.h> #include <linux/ioprio.h> #include <linux/blk-cgroup.h> #include "loop.h" #include <linux/uaccess.h> static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_ctl_mutex); static int max_part; static int part_shift; static int transfer_xor(struct loop_device *lo, int cmd, struct page *raw_page, unsigned raw_off, struct page *loop_page, unsigned loop_off, int size, sector_t real_block) { char *raw_buf = kmap_atomic(raw_page) + raw_off; char *loop_buf = kmap_atomic(loop_page) + loop_off; char *in, *out, *key; int i, keysize; if (cmd == READ) { in = raw_buf; out = loop_buf; } else { in = loop_buf; out = raw_buf; } key = lo->lo_encrypt_key; keysize = lo->lo_encrypt_key_size; for (i = 0; i < size; i++) *out++ = *in++ ^ key[(i & 511) % keysize]; kunmap_atomic(loop_buf); kunmap_atomic(raw_buf); cond_resched(); return 0; } static int xor_init(struct loop_device *lo, const struct loop_info64 *info) { if (unlikely(info->lo_encrypt_key_size <= 0)) return -EINVAL; return 0; } static struct loop_func_table none_funcs = { .number = LO_CRYPT_NONE, }; static struct loop_func_table xor_funcs = { .number = LO_CRYPT_XOR, .transfer = transfer_xor, .init = xor_init }; /* xfer_funcs[0] is special - its release function is never called */ static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = { &none_funcs, &xor_funcs }; static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file) { loff_t loopsize; /* Compute loopsize in bytes */ loopsize = i_size_read(file->f_mapping->host); if (offset > 0) loopsize -= offset; /* offset is beyond i_size, weird but possible */ if (loopsize < 0) return 0; if (sizelimit > 0 && sizelimit < loopsize) loopsize = sizelimit; /* * Unfortunately, if we want to do I/O on the device, * the number of 512-byte sectors has to fit into a sector_t. */ return loopsize >> 9; } static loff_t get_loop_size(struct loop_device *lo, struct file *file) { return get_size(lo->lo_offset, lo->lo_sizelimit, file); } static void __loop_update_dio(struct loop_device *lo, bool dio) { struct file *file = lo->lo_backing_file; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; unsigned short sb_bsize = 0; unsigned dio_align = 0; bool use_dio; if (inode->i_sb->s_bdev) { sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev); dio_align = sb_bsize - 1; } /* * We support direct I/O only if lo_offset is aligned with the * logical I/O size of backing device, and the logical block * size of loop is bigger than the backing device's and the loop * needn't transform transfer. * * TODO: the above condition may be loosed in the future, and * direct I/O may be switched runtime at that time because most * of requests in sane applications should be PAGE_SIZE aligned */ if (dio) { if (queue_logical_block_size(lo->lo_queue) >= sb_bsize && !(lo->lo_offset & dio_align) && mapping->a_ops->direct_IO && !lo->transfer) use_dio = true; else use_dio = false; } else { use_dio = false; } if (lo->use_dio == use_dio) return; /* flush dirty pages before changing direct IO */ vfs_fsync(file, 0); /* * The flag of LO_FLAGS_DIRECT_IO is handled similarly with * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup * will get updated by ioctl(LOOP_GET_STATUS) */ if (lo->lo_state == Lo_bound) blk_mq_freeze_queue(lo->lo_queue); lo->use_dio = use_dio; if (use_dio) { blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, lo->lo_queue); lo->lo_flags |= LO_FLAGS_DIRECT_IO; } else { blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; } if (lo->lo_state == Lo_bound) blk_mq_unfreeze_queue(lo->lo_queue); } /** * loop_set_size() - sets device size and notifies userspace * @lo: struct loop_device to set the size for * @size: new size of the loop device * * Callers must validate that the size passed into this function fits into * a sector_t, eg using loop_validate_size() */ static void loop_set_size(struct loop_device *lo, loff_t size) { struct block_device *bdev = lo->lo_device; bd_set_nr_sectors(bdev, size); if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, false)) kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); } static inline int lo_do_transfer(struct loop_device *lo, int cmd, struct page *rpage, unsigned roffs, struct page *lpage, unsigned loffs, int size, sector_t rblock) { int ret; ret = lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock); if (likely(!ret)) return 0; printk_ratelimited(KERN_ERR "loop: Transfer error at byte offset %llu, length %i.\n", (unsigned long long)rblock << 9, size); return ret; } static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) { struct iov_iter i; ssize_t bw; iov_iter_bvec(&i, WRITE, bvec, 1, bvec->bv_len); file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); file_end_write(file); if (likely(bw == bvec->bv_len)) return 0; printk_ratelimited(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n", (unsigned long long)*ppos, bvec->bv_len); if (bw >= 0) bw = -EIO; return bw; } static int lo_write_simple(struct loop_device *lo, struct request *rq, loff_t pos) { struct bio_vec bvec; struct req_iterator iter; int ret = 0; rq_for_each_segment(bvec, rq, iter) { ret = lo_write_bvec(lo->lo_backing_file, &bvec, &pos); if (ret < 0) break; cond_resched(); } return ret; } /* * This is the slow, transforming version that needs to double buffer the * data as it cannot do the transformations in place without having direct * access to the destination pages of the backing file. */ static int lo_write_transfer(struct loop_device *lo, struct request *rq, loff_t pos) { struct bio_vec bvec, b; struct req_iterator iter; struct page *page; int ret = 0; page = alloc_page(GFP_NOIO); if (unlikely(!page)) return -ENOMEM; rq_for_each_segment(bvec, rq, iter) { ret = lo_do_transfer(lo, WRITE, page, 0, bvec.bv_page, bvec.bv_offset, bvec.bv_len, pos >> 9); if (unlikely(ret)) break; b.bv_page = page; b.bv_offset = 0; b.bv_len = bvec.bv_len; ret = lo_write_bvec(lo->lo_backing_file, &b, &pos); if (ret < 0) break; } __free_page(page); return ret; } static int lo_read_simple(struct loop_device *lo, struct request *rq, loff_t pos) { struct bio_vec bvec; struct req_iterator iter; struct iov_iter i; ssize_t len; rq_for_each_segment(bvec, rq, iter) { iov_iter_bvec(&i, READ, &bvec, 1, bvec.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) return len; flush_dcache_page(bvec.bv_page); if (len != bvec.bv_len) { struct bio *bio; __rq_for_each_bio(bio, rq) zero_fill_bio(bio); break; } cond_resched(); } return 0; } static int lo_read_transfer(struct loop_device *lo, struct request *rq, loff_t pos) { struct bio_vec bvec, b; struct req_iterator iter; struct iov_iter i; struct page *page; ssize_t len; int ret = 0; page = alloc_page(GFP_NOIO); if (unlikely(!page)) return -ENOMEM; rq_for_each_segment(bvec, rq, iter) { loff_t offset = pos; b.bv_page = page; b.bv_offset = 0; b.bv_len = bvec.bv_len; iov_iter_bvec(&i, READ, &b, 1, b.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) { ret = len; goto out_free_page; } ret = lo_do_transfer(lo, READ, page, 0, bvec.bv_page, bvec.bv_offset, len, offset >> 9); if (ret) goto out_free_page; flush_dcache_page(bvec.bv_page); if (len != bvec.bv_len) { struct bio *bio; __rq_for_each_bio(bio, rq) zero_fill_bio(bio); break; } } ret = 0; out_free_page: __free_page(page); return ret; } static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, int mode) { /* * We use fallocate to manipulate the space mappings used by the image * a.k.a. discard/zerorange. However we do not support this if * encryption is enabled, because it may give an attacker useful * information. */ struct file *file = lo->lo_backing_file; struct request_queue *q = lo->lo_queue; int ret; mode |= FALLOC_FL_KEEP_SIZE; if (!blk_queue_discard(q)) { ret = -EOPNOTSUPP; goto out; } ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq)); if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP)) ret = -EIO; out: return ret; } static int lo_req_flush(struct loop_device *lo, struct request *rq) { struct file *file = lo->lo_backing_file; int ret = vfs_fsync(file, 0); if (unlikely(ret && ret != -EINVAL)) ret = -EIO; return ret; } static void lo_complete_rq(struct request *rq) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); blk_status_t ret = BLK_STS_OK; if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || req_op(rq) != REQ_OP_READ) { if (cmd->ret < 0) ret = errno_to_blk_status(cmd->ret); goto end_io; } /* * Short READ - if we got some data, advance our request and * retry it. If we got no data, end the rest with EIO. */ if (cmd->ret) { blk_update_request(rq, BLK_STS_OK, cmd->ret); cmd->ret = 0; blk_mq_requeue_request(rq, true); } else { if (cmd->use_aio) { struct bio *bio = rq->bio; while (bio) { zero_fill_bio(bio); bio = bio->bi_next; } } ret = BLK_STS_IOERR; end_io: blk_mq_end_request(rq, ret); } } static void lo_rw_aio_do_completion(struct loop_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); if (!atomic_dec_and_test(&cmd->ref)) return; kfree(cmd->bvec); cmd->bvec = NULL; if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq); } static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2) { struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb); if (cmd->css) css_put(cmd->css); cmd->ret = ret; lo_rw_aio_do_completion(cmd); } static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, loff_t pos, bool rw) { struct iov_iter iter; struct req_iterator rq_iter; struct bio_vec *bvec; struct request *rq = blk_mq_rq_from_pdu(cmd); struct bio *bio = rq->bio; struct file *file = lo->lo_backing_file; struct bio_vec tmp; unsigned int offset; int nr_bvec = 0; int ret; rq_for_each_bvec(tmp, rq, rq_iter) nr_bvec++; if (rq->bio != rq->biotail) { bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec), GFP_NOIO); if (!bvec) return -EIO; cmd->bvec = bvec; /* * The bios of the request may be started from the middle of * the 'bvec' because of bio splitting, so we can't directly * copy bio->bi_iov_vec to new bvec. The rq_for_each_bvec * API will take care of all details for us. */ rq_for_each_bvec(tmp, rq, rq_iter) { *bvec = tmp; bvec++; } bvec = cmd->bvec; offset = 0; } else { /* * Same here, this bio may be started from the middle of the * 'bvec' because of bio splitting, so offset from the bvec * must be passed to iov iterator */ offset = bio->bi_iter.bi_bvec_done; bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } atomic_set(&cmd->ref, 2); iov_iter_bvec(&iter, rw, bvec, nr_bvec, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; cmd->iocb.ki_filp = file; cmd->iocb.ki_complete = lo_rw_aio_complete; cmd->iocb.ki_flags = IOCB_DIRECT; cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); if (cmd->css) kthread_associate_blkcg(cmd->css); if (rw == WRITE) ret = call_write_iter(file, &cmd->iocb, &iter); else ret = call_read_iter(file, &cmd->iocb, &iter); lo_rw_aio_do_completion(cmd); kthread_associate_blkcg(NULL); if (ret != -EIOCBQUEUED) cmd->iocb.ki_complete(&cmd->iocb, ret, 0); return 0; } static int do_req_filebacked(struct loop_device *lo, struct request *rq) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset; /* * lo_write_simple and lo_read_simple should have been covered * by io submit style function like lo_rw_aio(), one blocker * is that lo_read_simple() need to call flush_dcache_page after * the page is written from kernel, and it isn't easy to handle * this in io submit style function which submits all segments * of the req at one time. And direct read IO doesn't need to * run flush_dcache_page(). */ switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); case REQ_OP_WRITE_ZEROES: /* * If the caller doesn't want deallocation, call zeroout to * write zeroes the range. Otherwise, punch them out. */ return lo_fallocate(lo, rq, pos, (rq->cmd_flags & REQ_NOUNMAP) ? FALLOC_FL_ZERO_RANGE : FALLOC_FL_PUNCH_HOLE); case REQ_OP_DISCARD: return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: if (lo->transfer) return lo_write_transfer(lo, rq, pos); else if (cmd->use_aio) return lo_rw_aio(lo, cmd, pos, WRITE); else return lo_write_simple(lo, rq, pos); case REQ_OP_READ: if (lo->transfer) return lo_read_transfer(lo, rq, pos); else if (cmd->use_aio) return lo_rw_aio(lo, cmd, pos, READ); else return lo_read_simple(lo, rq, pos); default: WARN_ON_ONCE(1); return -EIO; } } static inline void loop_update_dio(struct loop_device *lo) { __loop_update_dio(lo, (lo->lo_backing_file->f_flags & O_DIRECT) | lo->use_dio); } static void loop_reread_partitions(struct loop_device *lo, struct block_device *bdev) { int rc; mutex_lock(&bdev->bd_mutex); rc = bdev_disk_changed(bdev, false); mutex_unlock(&bdev->bd_mutex); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); } static inline int is_loop_device(struct file *file) { struct inode *i = file->f_mapping->host; return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR; } static int loop_validate_file(struct file *file, struct block_device *bdev) { struct inode *inode = file->f_mapping->host; struct file *f = file; /* Avoid recursion */ while (is_loop_device(f)) { struct loop_device *l; if (f->f_mapping->host->i_bdev == bdev) return -EBADF; l = f->f_mapping->host->i_bdev->bd_disk->private_data; if (l->lo_state != Lo_bound) { return -EINVAL; } f = l->lo_backing_file; } if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -EINVAL; return 0; } /* * loop_change_fd switched the backing store of a loopback device to * a new file. This is useful for operating system installers to free up * the original file and in High Availability environments to switch to * an alternative location for the content in case of server meltdown. * This can only work if the loop device is used read-only, and if the * new backing store is the same size and type as the old backing store. */ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, unsigned int arg) { struct file *file = NULL, *old_file; int error; bool partscan; error = mutex_lock_killable(&loop_ctl_mutex); if (error) return error; error = -ENXIO; if (lo->lo_state != Lo_bound) goto out_err; /* the loop device has to be read-only */ error = -EINVAL; if (!(lo->lo_flags & LO_FLAGS_READ_ONLY)) goto out_err; error = -EBADF; file = fget(arg); if (!file) goto out_err; error = loop_validate_file(file, bdev); if (error) goto out_err; old_file = lo->lo_backing_file; error = -EINVAL; /* size of the new backing store needs to be the same */ if (get_loop_size(lo, file) != get_loop_size(lo, old_file)) goto out_err; /* and ... switch */ blk_mq_freeze_queue(lo->lo_queue); mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); lo->lo_backing_file = file; lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping); mapping_set_gfp_mask(file->f_mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); loop_update_dio(lo); blk_mq_unfreeze_queue(lo->lo_queue); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; mutex_unlock(&loop_ctl_mutex); /* * We must drop file reference outside of loop_ctl_mutex as dropping * the file ref can take bd_mutex which creates circular locking * dependency. */ fput(old_file); if (partscan) loop_reread_partitions(lo, bdev); return 0; out_err: mutex_unlock(&loop_ctl_mutex); if (file) fput(file); return error; } /* loop sysfs attributes */ static ssize_t loop_attr_show(struct device *dev, char *page, ssize_t (*callback)(struct loop_device *, char *)) { struct gendisk *disk = dev_to_disk(dev); struct loop_device *lo = disk->private_data; return callback(lo, page); } #define LOOP_ATTR_RO(_name) \ static ssize_t loop_attr_##_name##_show(struct loop_device *, char *); \ static ssize_t loop_attr_do_show_##_name(struct device *d, \ struct device_attribute *attr, char *b) \ { \ return loop_attr_show(d, b, loop_attr_##_name##_show); \ } \ static struct device_attribute loop_attr_##_name = \ __ATTR(_name, 0444, loop_attr_do_show_##_name, NULL); static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf) { ssize_t ret; char *p = NULL; spin_lock_irq(&lo->lo_lock); if (lo->lo_backing_file) p = file_path(lo->lo_backing_file, buf, PAGE_SIZE - 1); spin_unlock_irq(&lo->lo_lock); if (IS_ERR_OR_NULL(p)) ret = PTR_ERR(p); else { ret = strlen(p); memmove(buf, p, ret); buf[ret++] = '\n'; buf[ret] = 0; } return ret; } static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_offset); } static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit); } static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf) { int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR); return sysfs_emit(buf, "%s\n", autoclear ? "1" : "0"); } static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf) { int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN); return sysfs_emit(buf, "%s\n", partscan ? "1" : "0"); } static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf) { int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO); return sysfs_emit(buf, "%s\n", dio ? "1" : "0"); } LOOP_ATTR_RO(backing_file); LOOP_ATTR_RO(offset); LOOP_ATTR_RO(sizelimit); LOOP_ATTR_RO(autoclear); LOOP_ATTR_RO(partscan); LOOP_ATTR_RO(dio); static struct attribute *loop_attrs[] = { &loop_attr_backing_file.attr, &loop_attr_offset.attr, &loop_attr_sizelimit.attr, &loop_attr_autoclear.attr, &loop_attr_partscan.attr, &loop_attr_dio.attr, NULL, }; static struct attribute_group loop_attribute_group = { .name = "loop", .attrs= loop_attrs, }; static void loop_sysfs_init(struct loop_device *lo) { lo->sysfs_inited = !sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj, &loop_attribute_group); } static void loop_sysfs_exit(struct loop_device *lo) { if (lo->sysfs_inited) sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj, &loop_attribute_group); } static void loop_config_discard(struct loop_device *lo) { struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct request_queue *q = lo->lo_queue; u32 granularity, max_discard_sectors; /* * If the backing device is a block device, mirror its zeroing * capability. Set the discard sectors to the block device's zeroing * capabilities because loop discards result in blkdev_issue_zeroout(), * not blkdev_issue_discard(). This maintains consistent behavior with * file-backed loop devices: discarded regions read back as zero. */ if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) { struct request_queue *backingq; backingq = bdev_get_queue(inode->i_bdev); max_discard_sectors = backingq->limits.max_write_zeroes_sectors; granularity = backingq->limits.discard_granularity ?: queue_physical_block_size(backingq); /* * We use punch hole to reclaim the free space used by the * image a.k.a. discard. However we do not support discard if * encryption is enabled, because it may give an attacker * useful information. */ } else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) { max_discard_sectors = 0; granularity = 0; } else { max_discard_sectors = UINT_MAX >> 9; granularity = inode->i_sb->s_blocksize; } if (max_discard_sectors) { q->limits.discard_granularity = granularity; blk_queue_max_discard_sectors(q, max_discard_sectors); blk_queue_max_write_zeroes_sectors(q, max_discard_sectors); blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } else { q->limits.discard_granularity = 0; blk_queue_max_discard_sectors(q, 0); blk_queue_max_write_zeroes_sectors(q, 0); blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); } q->limits.discard_alignment = 0; } static void loop_unprepare_queue(struct loop_device *lo) { kthread_flush_worker(&lo->worker); kthread_stop(lo->worker_task); } static int loop_kthread_worker_fn(void *worker_ptr) { current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; return kthread_worker_fn(worker_ptr); } static int loop_prepare_queue(struct loop_device *lo) { kthread_init_worker(&lo->worker); lo->worker_task = kthread_run(loop_kthread_worker_fn, &lo->worker, "loop%d", lo->lo_number); if (IS_ERR(lo->worker_task)) return -ENOMEM; set_user_nice(lo->worker_task, MIN_NICE); return 0; } static void loop_update_rotational(struct loop_device *lo) { struct file *file = lo->lo_backing_file; struct inode *file_inode = file->f_mapping->host; struct block_device *file_bdev = file_inode->i_sb->s_bdev; struct request_queue *q = lo->lo_queue; bool nonrot = true; /* not all filesystems (e.g. tmpfs) have a sb->s_bdev */ if (file_bdev) nonrot = blk_queue_nonrot(bdev_get_queue(file_bdev)); if (nonrot) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); else blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); } static int loop_release_xfer(struct loop_device *lo) { int err = 0; struct loop_func_table *xfer = lo->lo_encryption; if (xfer) { if (xfer->release) err = xfer->release(lo); lo->transfer = NULL; lo->lo_encryption = NULL; module_put(xfer->owner); } return err; } static int loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer, const struct loop_info64 *i) { int err = 0; if (xfer) { struct module *owner = xfer->owner; if (!try_module_get(owner)) return -EINVAL; if (xfer->init) err = xfer->init(lo, i); if (err) module_put(owner); else lo->lo_encryption = xfer; } return err; } /** * loop_set_status_from_info - configure device from loop_info * @lo: struct loop_device to configure * @info: struct loop_info64 to configure the device with * * Configures the loop device parameters according to the passed * in loop_info64 configuration. */ static int loop_set_status_from_info(struct loop_device *lo, const struct loop_info64 *info) { int err; struct loop_func_table *xfer; kuid_t uid = current_uid(); if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) return -EINVAL; err = loop_release_xfer(lo); if (err) return err; if (info->lo_encrypt_type) { unsigned int type = info->lo_encrypt_type; if (type >= MAX_LO_CRYPT) return -EINVAL; xfer = xfer_funcs[type]; if (xfer == NULL) return -EINVAL; } else xfer = NULL; err = loop_init_xfer(lo, xfer, info); if (err) return err; lo->lo_offset = info->lo_offset; lo->lo_sizelimit = info->lo_sizelimit; memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE); lo->lo_file_name[LO_NAME_SIZE-1] = 0; lo->lo_crypt_name[LO_NAME_SIZE-1] = 0; if (!xfer) xfer = &none_funcs; lo->transfer = xfer->transfer; lo->ioctl = xfer->ioctl; lo->lo_flags = info->lo_flags; lo->lo_encrypt_key_size = info->lo_encrypt_key_size; lo->lo_init[0] = info->lo_init[0]; lo->lo_init[1] = info->lo_init[1]; if (info->lo_encrypt_key_size) { memcpy(lo->lo_encrypt_key, info->lo_encrypt_key, info->lo_encrypt_key_size); lo->lo_key_owner = uid; } return 0; } static int loop_configure(struct loop_device *lo, fmode_t mode, struct block_device *bdev, const struct loop_config *config) { struct file *file; struct inode *inode; struct address_space *mapping; struct block_device *claimed_bdev = NULL; int error; loff_t size; bool partscan; unsigned short bsize; /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); error = -EBADF; file = fget(config->fd); if (!file) goto out; /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. */ if (!(mode & FMODE_EXCL)) { claimed_bdev = bdev->bd_contains; error = bd_prepare_to_claim(bdev, claimed_bdev, loop_configure); if (error) goto out_putf; } error = mutex_lock_killable(&loop_ctl_mutex); if (error) goto out_bdev; error = -EBUSY; if (lo->lo_state != Lo_unbound) goto out_unlock; error = loop_validate_file(file, bdev); if (error) goto out_unlock; mapping = file->f_mapping; inode = mapping->host; if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) { error = -EINVAL; goto out_unlock; } if (config->block_size) { error = blk_validate_block_size(config->block_size); if (error) goto out_unlock; } error = loop_set_status_from_info(lo, &config->info); if (error) goto out_unlock; if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) || !file->f_op->write_iter) lo->lo_flags |= LO_FLAGS_READ_ONLY; error = loop_prepare_queue(lo); if (error) goto out_unlock; set_device_ro(bdev, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO; lo->lo_device = bdev; lo->lo_backing_file = file; lo->old_gfp_mask = mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); if (!(lo->lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_write_cache(lo->lo_queue, true, false); if (config->block_size) bsize = config->block_size; else if ((lo->lo_backing_file->f_flags & O_DIRECT) && inode->i_sb->s_bdev) /* In case of direct I/O, match underlying block size */ bsize = bdev_logical_block_size(inode->i_sb->s_bdev); else bsize = 512; blk_queue_logical_block_size(lo->lo_queue, bsize); blk_queue_physical_block_size(lo->lo_queue, bsize); blk_queue_io_min(lo->lo_queue, bsize); loop_config_discard(lo); loop_update_rotational(lo); loop_update_dio(lo); loop_sysfs_init(lo); size = get_loop_size(lo, file); loop_set_size(lo, size); set_blocksize(bdev, S_ISBLK(inode->i_mode) ? block_size(inode->i_bdev) : PAGE_SIZE); lo->lo_state = Lo_bound; if (part_shift) lo->lo_flags |= LO_FLAGS_PARTSCAN; partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; if (partscan) lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; /* Grab the block_device to prevent its destruction after we * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev). */ bdgrab(bdev); mutex_unlock(&loop_ctl_mutex); if (partscan) loop_reread_partitions(lo, bdev); if (claimed_bdev) bd_abort_claiming(bdev, claimed_bdev, loop_configure); return 0; out_unlock: mutex_unlock(&loop_ctl_mutex); out_bdev: if (claimed_bdev) bd_abort_claiming(bdev, claimed_bdev, loop_configure); out_putf: fput(file); out: /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return error; } static int __loop_clr_fd(struct loop_device *lo, bool release) { struct file *filp = NULL; gfp_t gfp = lo->old_gfp_mask; struct block_device *bdev = lo->lo_device; int err = 0; bool partscan = false; int lo_number; mutex_lock(&loop_ctl_mutex); if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) { err = -ENXIO; goto out_unlock; } filp = lo->lo_backing_file; if (filp == NULL) { err = -EINVAL; goto out_unlock; } if (test_bit(QUEUE_FLAG_WC, &lo->lo_queue->queue_flags)) blk_queue_write_cache(lo->lo_queue, false, false); /* freeze request queue during the transition */ blk_mq_freeze_queue(lo->lo_queue); spin_lock_irq(&lo->lo_lock); lo->lo_backing_file = NULL; spin_unlock_irq(&lo->lo_lock); loop_release_xfer(lo); lo->transfer = NULL; lo->ioctl = NULL; lo->lo_device = NULL; lo->lo_encryption = NULL; lo->lo_offset = 0; lo->lo_sizelimit = 0; lo->lo_encrypt_key_size = 0; memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE); memset(lo->lo_crypt_name, 0, LO_NAME_SIZE); memset(lo->lo_file_name, 0, LO_NAME_SIZE); blk_queue_logical_block_size(lo->lo_queue, 512); blk_queue_physical_block_size(lo->lo_queue, 512); blk_queue_io_min(lo->lo_queue, 512); if (bdev) { bdput(bdev); invalidate_bdev(bdev); bdev->bd_inode->i_mapping->wb_err = 0; } set_capacity(lo->lo_disk, 0); loop_sysfs_exit(lo); if (bdev) { bd_set_nr_sectors(bdev, 0); /* let user-space know about this change */ kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); } mapping_set_gfp_mask(filp->f_mapping, gfp); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); blk_mq_unfreeze_queue(lo->lo_queue); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev; lo_number = lo->lo_number; loop_unprepare_queue(lo); out_unlock: mutex_unlock(&loop_ctl_mutex); if (partscan) { /* * bd_mutex has been held already in release path, so don't * acquire it if this function is called in such case. * * If the reread partition isn't from release path, lo_refcnt * must be at least one and it can only become zero when the * current holder is released. */ if (!release) mutex_lock(&bdev->bd_mutex); err = bdev_disk_changed(bdev, false); if (!release) mutex_unlock(&bdev->bd_mutex); if (err) pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", __func__, lo_number, err); /* Device is gone, no point in returning error */ err = 0; } /* * lo->lo_state is set to Lo_unbound here after above partscan has * finished. * * There cannot be anybody else entering __loop_clr_fd() as * lo->lo_backing_file is already cleared and Lo_rundown state * protects us from all the other places trying to change the 'lo' * device. */ mutex_lock(&loop_ctl_mutex); lo->lo_flags = 0; if (!part_shift) lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; lo->lo_state = Lo_unbound; mutex_unlock(&loop_ctl_mutex); /* * Need not hold loop_ctl_mutex to fput backing file. * Calling fput holding loop_ctl_mutex triggers a circular * lock dependency possibility warning as fput can take * bd_mutex which is usually taken before loop_ctl_mutex. */ if (filp) fput(filp); return err; } static int loop_clr_fd(struct loop_device *lo) { int err; err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; if (lo->lo_state != Lo_bound) { mutex_unlock(&loop_ctl_mutex); return -ENXIO; } /* * If we've explicitly asked to tear down the loop device, * and it has an elevated reference count, set it for auto-teardown when * the last reference goes away. This stops $!~#$@ udev from * preventing teardown because it decided that it needs to run blkid on * the loopback device whenever they appear. xfstests is notorious for * failing tests because blkid via udev races with a losetup * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d * command to fail with EBUSY. */ if (atomic_read(&lo->lo_refcnt) > 1) { lo->lo_flags |= LO_FLAGS_AUTOCLEAR; mutex_unlock(&loop_ctl_mutex); return 0; } lo->lo_state = Lo_rundown; mutex_unlock(&loop_ctl_mutex); return __loop_clr_fd(lo, false); } static int loop_set_status(struct loop_device *lo, const struct loop_info64 *info) { int err; struct block_device *bdev; kuid_t uid = current_uid(); int prev_lo_flags; bool partscan = false; bool size_changed = false; err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; if (lo->lo_encrypt_key_size && !uid_eq(lo->lo_key_owner, uid) && !capable(CAP_SYS_ADMIN)) { err = -EPERM; goto out_unlock; } if (lo->lo_state != Lo_bound) { err = -ENXIO; goto out_unlock; } if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) { size_changed = true; sync_blockdev(lo->lo_device); invalidate_bdev(lo->lo_device); } /* I/O need to be drained during transfer transition */ blk_mq_freeze_queue(lo->lo_queue); if (size_changed && lo->lo_device->bd_inode->i_mapping->nrpages) { /* If any pages were dirtied after invalidate_bdev(), try again */ err = -EAGAIN; pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", __func__, lo->lo_number, lo->lo_file_name, lo->lo_device->bd_inode->i_mapping->nrpages); goto out_unfreeze; } prev_lo_flags = lo->lo_flags; err = loop_set_status_from_info(lo, info); if (err) goto out_unfreeze; /* Mask out flags that can't be set using LOOP_SET_STATUS. */ lo->lo_flags &= LOOP_SET_STATUS_SETTABLE_FLAGS; /* For those flags, use the previous values instead */ lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_SETTABLE_FLAGS; /* For flags that can't be cleared, use previous values too */ lo->lo_flags |= prev_lo_flags & ~LOOP_SET_STATUS_CLEARABLE_FLAGS; if (size_changed) { loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit, lo->lo_backing_file); loop_set_size(lo, new_size); } loop_config_discard(lo); /* update dio if lo_offset or transfer is changed */ __loop_update_dio(lo, lo->use_dio); out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) && !(prev_lo_flags & LO_FLAGS_PARTSCAN)) { lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; bdev = lo->lo_device; partscan = true; } out_unlock: mutex_unlock(&loop_ctl_mutex); if (partscan) loop_reread_partitions(lo, bdev); return err; } static int loop_get_status(struct loop_device *lo, struct loop_info64 *info) { struct path path; struct kstat stat; int ret; ret = mutex_lock_killable(&loop_ctl_mutex); if (ret) return ret; if (lo->lo_state != Lo_bound) { mutex_unlock(&loop_ctl_mutex); return -ENXIO; } memset(info, 0, sizeof(*info)); info->lo_number = lo->lo_number; info->lo_offset = lo->lo_offset; info->lo_sizelimit = lo->lo_sizelimit; info->lo_flags = lo->lo_flags; memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE); memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE); info->lo_encrypt_type = lo->lo_encryption ? lo->lo_encryption->number : 0; if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) { info->lo_encrypt_key_size = lo->lo_encrypt_key_size; memcpy(info->lo_encrypt_key, lo->lo_encrypt_key, lo->lo_encrypt_key_size); } /* Drop loop_ctl_mutex while we call into the filesystem. */ path = lo->lo_backing_file->f_path; path_get(&path); mutex_unlock(&loop_ctl_mutex); ret = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT); if (!ret) { info->lo_device = huge_encode_dev(stat.dev); info->lo_inode = stat.ino; info->lo_rdevice = huge_encode_dev(stat.rdev); } path_put(&path); return ret; } static void loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info64) { memset(info64, 0, sizeof(*info64)); info64->lo_number = info->lo_number; info64->lo_device = info->lo_device; info64->lo_inode = info->lo_inode; info64->lo_rdevice = info->lo_rdevice; info64->lo_offset = info->lo_offset; info64->lo_sizelimit = 0; info64->lo_encrypt_type = info->lo_encrypt_type; info64->lo_encrypt_key_size = info->lo_encrypt_key_size; info64->lo_flags = info->lo_flags; info64->lo_init[0] = info->lo_init[0]; info64->lo_init[1] = info->lo_init[1]; if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI) memcpy(info64->lo_crypt_name, info->lo_name, LO_NAME_SIZE); else memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE); memcpy(info64->lo_encrypt_key, info->lo_encrypt_key, LO_KEY_SIZE); } static int loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info) { memset(info, 0, sizeof(*info)); info->lo_number = info64->lo_number; info->lo_device = info64->lo_device; info->lo_inode = info64->lo_inode; info->lo_rdevice = info64->lo_rdevice; info->lo_offset = info64->lo_offset; info->lo_encrypt_type = info64->lo_encrypt_type; info->lo_encrypt_key_size = info64->lo_encrypt_key_size; info->lo_flags = info64->lo_flags; info->lo_init[0] = info64->lo_init[0]; info->lo_init[1] = info64->lo_init[1]; if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI) memcpy(info->lo_name, info64->lo_crypt_name, LO_NAME_SIZE); else memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE); memcpy(info->lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE); /* error in case values were truncated */ if (info->lo_device != info64->lo_device || info->lo_rdevice != info64->lo_rdevice || info->lo_inode != info64->lo_inode || info->lo_offset != info64->lo_offset) return -EOVERFLOW; return 0; } static int loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg) { struct loop_info info; struct loop_info64 info64; if (copy_from_user(&info, arg, sizeof (struct loop_info))) return -EFAULT; loop_info64_from_old(&info, &info64); return loop_set_status(lo, &info64); } static int loop_set_status64(struct loop_device *lo, const struct loop_info64 __user *arg) { struct loop_info64 info64; if (copy_from_user(&info64, arg, sizeof (struct loop_info64))) return -EFAULT; return loop_set_status(lo, &info64); } static int loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) { struct loop_info info; struct loop_info64 info64; int err; if (!arg) return -EINVAL; err = loop_get_status(lo, &info64); if (!err) err = loop_info64_to_old(&info64, &info); if (!err && copy_to_user(arg, &info, sizeof(info))) err = -EFAULT; return err; } static int loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { struct loop_info64 info64; int err; if (!arg) return -EINVAL; err = loop_get_status(lo, &info64); if (!err && copy_to_user(arg, &info64, sizeof(info64))) err = -EFAULT; return err; } static int loop_set_capacity(struct loop_device *lo) { loff_t size; if (unlikely(lo->lo_state != Lo_bound)) return -ENXIO; size = get_loop_size(lo, lo->lo_backing_file); loop_set_size(lo, size); return 0; } static int loop_set_dio(struct loop_device *lo, unsigned long arg) { int error = -ENXIO; if (lo->lo_state != Lo_bound) goto out; __loop_update_dio(lo, !!arg); if (lo->use_dio == !!arg) return 0; error = -EINVAL; out: return error; } static int loop_set_block_size(struct loop_device *lo, unsigned long arg) { int err = 0; if (lo->lo_state != Lo_bound) return -ENXIO; err = blk_validate_block_size(arg); if (err) return err; if (lo->lo_queue->limits.logical_block_size == arg) return 0; sync_blockdev(lo->lo_device); invalidate_bdev(lo->lo_device); blk_mq_freeze_queue(lo->lo_queue); /* invalidate_bdev should have truncated all the pages */ if (lo->lo_device->bd_inode->i_mapping->nrpages) { err = -EAGAIN; pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", __func__, lo->lo_number, lo->lo_file_name, lo->lo_device->bd_inode->i_mapping->nrpages); goto out_unfreeze; } blk_queue_logical_block_size(lo->lo_queue, arg); blk_queue_physical_block_size(lo->lo_queue, arg); blk_queue_io_min(lo->lo_queue, arg); loop_update_dio(lo); out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); return err; } static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd, unsigned long arg) { int err; err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; switch (cmd) { case LOOP_SET_CAPACITY: err = loop_set_capacity(lo); break; case LOOP_SET_DIRECT_IO: err = loop_set_dio(lo, arg); break; case LOOP_SET_BLOCK_SIZE: err = loop_set_block_size(lo, arg); break; default: err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } mutex_unlock(&loop_ctl_mutex); return err; } static int lo_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; void __user *argp = (void __user *) arg; int err; switch (cmd) { case LOOP_SET_FD: { /* * Legacy case - pass in a zeroed out struct loop_config with * only the file descriptor set , which corresponds with the * default parameters we'd have used otherwise. */ struct loop_config config; memset(&config, 0, sizeof(config)); config.fd = arg; return loop_configure(lo, mode, bdev, &config); } case LOOP_CONFIGURE: { struct loop_config config; if (copy_from_user(&config, argp, sizeof(config))) return -EFAULT; return loop_configure(lo, mode, bdev, &config); } case LOOP_CHANGE_FD: return loop_change_fd(lo, bdev, arg); case LOOP_CLR_FD: return loop_clr_fd(lo); case LOOP_SET_STATUS: err = -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { err = loop_set_status_old(lo, argp); } break; case LOOP_GET_STATUS: return loop_get_status_old(lo, argp); case LOOP_SET_STATUS64: err = -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { err = loop_set_status64(lo, argp); } break; case LOOP_GET_STATUS64: return loop_get_status64(lo, argp); case LOOP_SET_CAPACITY: case LOOP_SET_DIRECT_IO: case LOOP_SET_BLOCK_SIZE: if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN)) return -EPERM; fallthrough; default: err = lo_simple_ioctl(lo, cmd, arg); break; } return err; } #ifdef CONFIG_COMPAT struct compat_loop_info { compat_int_t lo_number; /* ioctl r/o */ compat_dev_t lo_device; /* ioctl r/o */ compat_ulong_t lo_inode; /* ioctl r/o */ compat_dev_t lo_rdevice; /* ioctl r/o */ compat_int_t lo_offset; compat_int_t lo_encrypt_type; compat_int_t lo_encrypt_key_size; /* ioctl w/o */ compat_int_t lo_flags; /* ioctl r/o */ char lo_name[LO_NAME_SIZE]; unsigned char lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */ compat_ulong_t lo_init[2]; char reserved[4]; }; /* * Transfer 32-bit compatibility structure in userspace to 64-bit loop info * - noinlined to reduce stack space usage in main part of driver */ static noinline int loop_info64_from_compat(const struct compat_loop_info __user *arg, struct loop_info64 *info64) { struct compat_loop_info info; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; memset(info64, 0, sizeof(*info64)); info64->lo_number = info.lo_number; info64->lo_device = info.lo_device; info64->lo_inode = info.lo_inode; info64->lo_rdevice = info.lo_rdevice; info64->lo_offset = info.lo_offset; info64->lo_sizelimit = 0; info64->lo_encrypt_type = info.lo_encrypt_type; info64->lo_encrypt_key_size = info.lo_encrypt_key_size; info64->lo_flags = info.lo_flags; info64->lo_init[0] = info.lo_init[0]; info64->lo_init[1] = info.lo_init[1]; if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI) memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE); else memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE); memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE); return 0; } /* * Transfer 64-bit loop info to 32-bit compatibility structure in userspace * - noinlined to reduce stack space usage in main part of driver */ static noinline int loop_info64_to_compat(const struct loop_info64 *info64, struct compat_loop_info __user *arg) { struct compat_loop_info info; memset(&info, 0, sizeof(info)); info.lo_number = info64->lo_number; info.lo_device = info64->lo_device; info.lo_inode = info64->lo_inode; info.lo_rdevice = info64->lo_rdevice; info.lo_offset = info64->lo_offset; info.lo_encrypt_type = info64->lo_encrypt_type; info.lo_encrypt_key_size = info64->lo_encrypt_key_size; info.lo_flags = info64->lo_flags; info.lo_init[0] = info64->lo_init[0]; info.lo_init[1] = info64->lo_init[1]; if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI) memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE); else memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE); memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE); /* error in case values were truncated */ if (info.lo_device != info64->lo_device || info.lo_rdevice != info64->lo_rdevice || info.lo_inode != info64->lo_inode || info.lo_offset != info64->lo_offset || info.lo_init[0] != info64->lo_init[0] || info.lo_init[1] != info64->lo_init[1]) return -EOVERFLOW; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int loop_set_status_compat(struct loop_device *lo, const struct compat_loop_info __user *arg) { struct loop_info64 info64; int ret; ret = loop_info64_from_compat(arg, &info64); if (ret < 0) return ret; return loop_set_status(lo, &info64); } static int loop_get_status_compat(struct loop_device *lo, struct compat_loop_info __user *arg) { struct loop_info64 info64; int err; if (!arg) return -EINVAL; err = loop_get_status(lo, &info64); if (!err) err = loop_info64_to_compat(&info64, arg); return err; } static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; int err; switch(cmd) { case LOOP_SET_STATUS: err = loop_set_status_compat(lo, (const struct compat_loop_info __user *)arg); break; case LOOP_GET_STATUS: err = loop_get_status_compat(lo, (struct compat_loop_info __user *)arg); break; case LOOP_SET_CAPACITY: case LOOP_CLR_FD: case LOOP_GET_STATUS64: case LOOP_SET_STATUS64: case LOOP_CONFIGURE: arg = (unsigned long) compat_ptr(arg); fallthrough; case LOOP_SET_FD: case LOOP_CHANGE_FD: case LOOP_SET_BLOCK_SIZE: case LOOP_SET_DIRECT_IO: err = lo_ioctl(bdev, mode, cmd, arg); break; default: err = -ENOIOCTLCMD; break; } return err; } #endif static int lo_open(struct block_device *bdev, fmode_t mode) { struct loop_device *lo; int err; err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; lo = bdev->bd_disk->private_data; if (!lo) { err = -ENXIO; goto out; } atomic_inc(&lo->lo_refcnt); out: mutex_unlock(&loop_ctl_mutex); return err; } static void lo_release(struct gendisk *disk, fmode_t mode) { struct loop_device *lo; mutex_lock(&loop_ctl_mutex); lo = disk->private_data; if (atomic_dec_return(&lo->lo_refcnt)) goto out_unlock; if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { if (lo->lo_state != Lo_bound) goto out_unlock; lo->lo_state = Lo_rundown; mutex_unlock(&loop_ctl_mutex); /* * In autoclear mode, stop the loop thread * and remove configuration after last close. */ __loop_clr_fd(lo, true); return; } else if (lo->lo_state == Lo_bound) { /* * Otherwise keep thread (if running) and config, * but flush possible ongoing bios in thread. */ blk_mq_freeze_queue(lo->lo_queue); blk_mq_unfreeze_queue(lo->lo_queue); } out_unlock: mutex_unlock(&loop_ctl_mutex); } static const struct block_device_operations lo_fops = { .owner = THIS_MODULE, .open = lo_open, .release = lo_release, .ioctl = lo_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = lo_compat_ioctl, #endif }; /* * And now the modules code and kernel interface. */ static int max_loop; module_param(max_loop, int, 0444); MODULE_PARM_DESC(max_loop, "Maximum number of loop devices"); module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR); int loop_register_transfer(struct loop_func_table *funcs) { unsigned int n = funcs->number; if (n >= MAX_LO_CRYPT || xfer_funcs[n]) return -EINVAL; xfer_funcs[n] = funcs; return 0; } static int unregister_transfer_cb(int id, void *ptr, void *data) { struct loop_device *lo = ptr; struct loop_func_table *xfer = data; mutex_lock(&loop_ctl_mutex); if (lo->lo_encryption == xfer) loop_release_xfer(lo); mutex_unlock(&loop_ctl_mutex); return 0; } int loop_unregister_transfer(int number) { unsigned int n = number; struct loop_func_table *xfer; if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL) return -EINVAL; xfer_funcs[n] = NULL; idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer); return 0; } EXPORT_SYMBOL(loop_register_transfer); EXPORT_SYMBOL(loop_unregister_transfer); static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *rq = bd->rq; struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); struct loop_device *lo = rq->q->queuedata; blk_mq_start_request(rq); if (lo->lo_state != Lo_bound) return BLK_STS_IOERR; switch (req_op(rq)) { case REQ_OP_FLUSH: case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: cmd->use_aio = false; break; default: cmd->use_aio = lo->use_dio; break; } /* always use the first bio's css */ #ifdef CONFIG_BLK_CGROUP if (cmd->use_aio && rq->bio && rq->bio->bi_blkg) { cmd->css = &bio_blkcg(rq->bio)->css; css_get(cmd->css); } else #endif cmd->css = NULL; kthread_queue_work(&lo->worker, &cmd->work); return BLK_STS_OK; } static void loop_handle_cmd(struct loop_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); const bool write = op_is_write(req_op(rq)); struct loop_device *lo = rq->q->queuedata; int ret = 0; if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) { ret = -EIO; goto failed; } ret = do_req_filebacked(lo, rq); failed: /* complete non-aio request */ if (!cmd->use_aio || ret) { if (ret == -EOPNOTSUPP) cmd->ret = ret; else cmd->ret = ret ? -EIO : 0; if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq); } } static void loop_queue_work(struct kthread_work *work) { struct loop_cmd *cmd = container_of(work, struct loop_cmd, work); loop_handle_cmd(cmd); } static int loop_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, unsigned int numa_node) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); kthread_init_work(&cmd->work, loop_queue_work); return 0; } static const struct blk_mq_ops loop_mq_ops = { .queue_rq = loop_queue_rq, .init_request = loop_init_request, .complete = lo_complete_rq, }; static int loop_add(struct loop_device **l, int i) { struct loop_device *lo; struct gendisk *disk; int err; err = -ENOMEM; lo = kzalloc(sizeof(*lo), GFP_KERNEL); if (!lo) goto out; lo->lo_state = Lo_unbound; /* allocate id, if @id >= 0, we're requesting that specific id */ if (i >= 0) { err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL); if (err == -ENOSPC) err = -EEXIST; } else { err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL); } if (err < 0) goto out_free_dev; i = err; err = -ENOMEM; lo->tag_set.ops = &loop_mq_ops; lo->tag_set.nr_hw_queues = 1; lo->tag_set.queue_depth = 128; lo->tag_set.numa_node = NUMA_NO_NODE; lo->tag_set.cmd_size = sizeof(struct loop_cmd); lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_STACKING; lo->tag_set.driver_data = lo; err = blk_mq_alloc_tag_set(&lo->tag_set); if (err) goto out_free_idr; lo->lo_queue = blk_mq_init_queue(&lo->tag_set); if (IS_ERR(lo->lo_queue)) { err = PTR_ERR(lo->lo_queue); goto out_cleanup_tags; } lo->lo_queue->queuedata = lo; blk_queue_max_hw_sectors(lo->lo_queue, BLK_DEF_MAX_SECTORS); /* * By default, we do buffer IO, so it doesn't make sense to enable * merge because the I/O submitted to backing file is handled page by * page. For directio mode, merge does help to dispatch bigger request * to underlayer disk. We will enable merge once directio is enabled. */ blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); err = -ENOMEM; disk = lo->lo_disk = alloc_disk(1 << part_shift); if (!disk) goto out_free_queue; /* * Disable partition scanning by default. The in-kernel partition * scanning can be requested individually per-device during its * setup. Userspace can always add and remove partitions from all * devices. The needed partition minors are allocated from the * extended minor space, the main loop device numbers will continue * to match the loop minors, regardless of the number of partitions * used. * * If max_part is given, partition scanning is globally enabled for * all loop devices. The minors for the main loop devices will be * multiples of max_part. * * Note: Global-for-all-devices, set-only-at-init, read-only module * parameteters like 'max_loop' and 'max_part' make things needlessly * complicated, are too static, inflexible and may surprise * userspace tools. Parameters like this in general should be avoided. */ if (!part_shift) disk->flags |= GENHD_FL_NO_PART_SCAN; disk->flags |= GENHD_FL_EXT_DEVT; atomic_set(&lo->lo_refcnt, 0); lo->lo_number = i; spin_lock_init(&lo->lo_lock); disk->major = LOOP_MAJOR; disk->first_minor = i << part_shift; disk->fops = &lo_fops; disk->private_data = lo; disk->queue = lo->lo_queue; sprintf(disk->disk_name, "loop%d", i); add_disk(disk); *l = lo; return lo->lo_number; out_free_queue: blk_cleanup_queue(lo->lo_queue); out_cleanup_tags: blk_mq_free_tag_set(&lo->tag_set); out_free_idr: idr_remove(&loop_index_idr, i); out_free_dev: kfree(lo); out: return err; } static void loop_remove(struct loop_device *lo) { del_gendisk(lo->lo_disk); blk_cleanup_queue(lo->lo_queue); blk_mq_free_tag_set(&lo->tag_set); put_disk(lo->lo_disk); kfree(lo); } static int find_free_cb(int id, void *ptr, void *data) { struct loop_device *lo = ptr; struct loop_device **l = data; if (lo->lo_state == Lo_unbound) { *l = lo; return 1; } return 0; } static int loop_lookup(struct loop_device **l, int i) { struct loop_device *lo; int ret = -ENODEV; if (i < 0) { int err; err = idr_for_each(&loop_index_idr, &find_free_cb, &lo); if (err == 1) { *l = lo; ret = lo->lo_number; } goto out; } /* lookup and return a specific i */ lo = idr_find(&loop_index_idr, i); if (lo) { *l = lo; ret = lo->lo_number; } out: return ret; } static struct kobject *loop_probe(dev_t dev, int *part, void *data) { struct loop_device *lo; struct kobject *kobj; int err; mutex_lock(&loop_ctl_mutex); err = loop_lookup(&lo, MINOR(dev) >> part_shift); if (err < 0) err = loop_add(&lo, MINOR(dev) >> part_shift); if (err < 0) kobj = NULL; else kobj = get_disk_and_module(lo->lo_disk); mutex_unlock(&loop_ctl_mutex); *part = 0; return kobj; } static long loop_control_ioctl(struct file *file, unsigned int cmd, unsigned long parm) { struct loop_device *lo; int ret; ret = mutex_lock_killable(&loop_ctl_mutex); if (ret) return ret; ret = -ENOSYS; switch (cmd) { case LOOP_CTL_ADD: ret = loop_lookup(&lo, parm); if (ret >= 0) { ret = -EEXIST; break; } ret = loop_add(&lo, parm); break; case LOOP_CTL_REMOVE: ret = loop_lookup(&lo, parm); if (ret < 0) break; if (lo->lo_state != Lo_unbound) { ret = -EBUSY; break; } if (atomic_read(&lo->lo_refcnt) > 0) { ret = -EBUSY; break; } lo->lo_disk->private_data = NULL; idr_remove(&loop_index_idr, lo->lo_number); loop_remove(lo); break; case LOOP_CTL_GET_FREE: ret = loop_lookup(&lo, -1); if (ret >= 0) break; ret = loop_add(&lo, -1); } mutex_unlock(&loop_ctl_mutex); return ret; } static const struct file_operations loop_ctl_fops = { .open = nonseekable_open, .unlocked_ioctl = loop_control_ioctl, .compat_ioctl = loop_control_ioctl, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice loop_misc = { .minor = LOOP_CTRL_MINOR, .name = "loop-control", .fops = &loop_ctl_fops, }; MODULE_ALIAS_MISCDEV(LOOP_CTRL_MINOR); MODULE_ALIAS("devname:loop-control"); static int __init loop_init(void) { int i, nr; unsigned long range; struct loop_device *lo; int err; part_shift = 0; if (max_part > 0) { part_shift = fls(max_part); /* * Adjust max_part according to part_shift as it is exported * to user space so that user can decide correct minor number * if [s]he want to create more devices. * * Note that -1 is required because partition 0 is reserved * for the whole disk. */ max_part = (1UL << part_shift) - 1; } if ((1UL << part_shift) > DISK_MAX_PARTS) { err = -EINVAL; goto err_out; } if (max_loop > 1UL << (MINORBITS - part_shift)) { err = -EINVAL; goto err_out; } /* * If max_loop is specified, create that many devices upfront. * This also becomes a hard limit. If max_loop is not specified, * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module * init time. Loop devices can be requested on-demand with the * /dev/loop-control interface, or be instantiated by accessing * a 'dead' device node. */ if (max_loop) { nr = max_loop; range = max_loop << part_shift; } else { nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT; range = 1UL << MINORBITS; } err = misc_register(&loop_misc); if (err < 0) goto err_out; if (register_blkdev(LOOP_MAJOR, "loop")) { err = -EIO; goto misc_out; } blk_register_region(MKDEV(LOOP_MAJOR, 0), range, THIS_MODULE, loop_probe, NULL, NULL); /* pre-create number of devices given by config or max_loop */ mutex_lock(&loop_ctl_mutex); for (i = 0; i < nr; i++) loop_add(&lo, i); mutex_unlock(&loop_ctl_mutex); printk(KERN_INFO "loop: module loaded\n"); return 0; misc_out: misc_deregister(&loop_misc); err_out: return err; } static int loop_exit_cb(int id, void *ptr, void *data) { struct loop_device *lo = ptr; loop_remove(lo); return 0; } static void __exit loop_exit(void) { unsigned long range; range = max_loop ? max_loop << part_shift : 1UL << MINORBITS; mutex_lock(&loop_ctl_mutex); idr_for_each(&loop_index_idr, &loop_exit_cb, NULL); idr_destroy(&loop_index_idr); blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range); unregister_blkdev(LOOP_MAJOR, "loop"); misc_deregister(&loop_misc); mutex_unlock(&loop_ctl_mutex); } module_init(loop_init); module_exit(loop_exit); #ifndef MODULE static int __init max_loop_setup(char *str) { max_loop = simple_strtol(str, NULL, 0); return 1; } __setup("max_loop=", max_loop_setup); #endif
1102 1029 658 658 453 862 360 861 361 1640 1257 906 905 904 1640 453 288 289 687 686 686 1575 1576 1574 1571 16 16 1453 124 48 48 124 26 26 125 7 43 21 49 126 125 55 70 124 1533 1533 1523 490 1491 453 1463 1638 265 1640 1635 1635 322 1636 629 1635 124 1639 1642 1640 1569 1742 453 453 453 453 453 453 453 452 453 453 453 453 453 453 3 453 453 398 397 398 398 398 398 453 8 8 8 8 8 8 445 659 659 181 478 445 1 1 122 122 5 5 5 5 5 5 5 5 5 5 5 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // SPDX-License-Identifier: GPL-2.0 /* * NETLINK Generic Netlink Family * * Authors: Jamal Hadi Salim * Thomas Graf <tgraf@suug.ch> * Johannes Berg <johannes@sipsolutions.net> */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/mutex.h> #include <linux/bitmap.h> #include <linux/rwsem.h> #include <linux/idr.h> #include <net/sock.h> #include <net/genetlink.h> static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */ static DECLARE_RWSEM(cb_lock); atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0); DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq); void genl_lock(void) { mutex_lock(&genl_mutex); } EXPORT_SYMBOL(genl_lock); void genl_unlock(void) { mutex_unlock(&genl_mutex); } EXPORT_SYMBOL(genl_unlock); #ifdef CONFIG_LOCKDEP bool lockdep_genl_is_held(void) { return lockdep_is_held(&genl_mutex); } EXPORT_SYMBOL(lockdep_genl_is_held); #endif static void genl_lock_all(void) { down_write(&cb_lock); genl_lock(); } static void genl_unlock_all(void) { genl_unlock(); up_write(&cb_lock); } static DEFINE_IDR(genl_fam_idr); /* * Bitmap of multicast groups that are currently in use. * * To avoid an allocation at boot of just one unsigned long, * declare it global instead. * Bit 0 is marked as already used since group 0 is invalid. * Bit 1 is marked as already used since the drop-monitor code * abuses the API and thinks it can statically use group 1. * That group will typically conflict with other groups that * any proper users use. * Bit 16 is marked as used since it's used for generic netlink * and the code no longer marks pre-reserved IDs as used. * Bit 17 is marked as already used since the VFS quota code * also abused this API and relied on family == group ID, we * cater to that by giving it a static family and group ID. * Bit 18 is marked as already used since the PMCRAID driver * did the same thing as the VFS quota code (maybe copied?) */ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) | BIT(GENL_ID_VFS_DQUOT) | BIT(GENL_ID_PMCRAID); static unsigned long *mc_groups = &mc_group_start; static unsigned long mc_groups_longs = 1; static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id); static const struct genl_family *genl_family_find_byid(unsigned int id) { return idr_find(&genl_fam_idr, id); } static const struct genl_family *genl_family_find_byname(char *name) { const struct genl_family *family; unsigned int id; idr_for_each_entry(&genl_fam_idr, family, id) if (strcmp(family->name, name) == 0) return family; return NULL; } static int genl_get_cmd_cnt(const struct genl_family *family) { return family->n_ops + family->n_small_ops; } static void genl_op_from_full(const struct genl_family *family, unsigned int i, struct genl_ops *op) { *op = family->ops[i]; if (!op->maxattr) op->maxattr = family->maxattr; if (!op->policy) op->policy = family->policy; } static int genl_get_cmd_full(u32 cmd, const struct genl_family *family, struct genl_ops *op) { int i; for (i = 0; i < family->n_ops; i++) if (family->ops[i].cmd == cmd) { genl_op_from_full(family, i, op); return 0; } return -ENOENT; } static void genl_op_from_small(const struct genl_family *family, unsigned int i, struct genl_ops *op) { memset(op, 0, sizeof(*op)); op->doit = family->small_ops[i].doit; op->dumpit = family->small_ops[i].dumpit; op->cmd = family->small_ops[i].cmd; op->internal_flags = family->small_ops[i].internal_flags; op->flags = family->small_ops[i].flags; op->validate = family->small_ops[i].validate; op->maxattr = family->maxattr; op->policy = family->policy; } static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, struct genl_ops *op) { int i; for (i = 0; i < family->n_small_ops; i++) if (family->small_ops[i].cmd == cmd) { genl_op_from_small(family, i, op); return 0; } return -ENOENT; } static int genl_get_cmd(u32 cmd, const struct genl_family *family, struct genl_ops *op) { if (!genl_get_cmd_full(cmd, family, op)) return 0; return genl_get_cmd_small(cmd, family, op); } static void genl_get_cmd_by_index(unsigned int i, const struct genl_family *family, struct genl_ops *op) { if (i < family->n_ops) genl_op_from_full(family, i, op); else if (i < family->n_ops + family->n_small_ops) genl_op_from_small(family, i - family->n_ops, op); else WARN_ON_ONCE(1); } static int genl_allocate_reserve_groups(int n_groups, int *first_id) { unsigned long *new_groups; int start = 0; int i; int id; bool fits; do { if (start == 0) id = find_first_zero_bit(mc_groups, mc_groups_longs * BITS_PER_LONG); else id = find_next_zero_bit(mc_groups, mc_groups_longs * BITS_PER_LONG, start); fits = true; for (i = id; i < min_t(int, id + n_groups, mc_groups_longs * BITS_PER_LONG); i++) { if (test_bit(i, mc_groups)) { start = i; fits = false; break; } } if (id + n_groups > mc_groups_longs * BITS_PER_LONG) { unsigned long new_longs = mc_groups_longs +