Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ #define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ #include <asm-generic/pgtable-nop4d.h> #ifndef __ASSEMBLY__ #include <linux/mmdebug.h> #include <linux/bug.h> #include <linux/sizes.h> #endif /* * Common bits between hash and Radix page table */ #define _PAGE_EXEC 0x00001 /* execute permission */ #define _PAGE_WRITE 0x00002 /* write access allowed */ #define _PAGE_READ 0x00004 /* read access allowed */ #define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) #define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC) #define _PAGE_PRIVILEGED 0x00008 /* kernel access only */ #define _PAGE_SAO 0x00010 /* Strong access order */ #define _PAGE_NON_IDEMPOTENT 0x00020 /* non idempotent memory */ #define _PAGE_TOLERANT 0x00030 /* tolerant memory, cache inhibited */ #define _PAGE_DIRTY 0x00080 /* C: page changed */ #define _PAGE_ACCESSED 0x00100 /* R: page referenced */ /* * Software bits */ #define _RPAGE_SW0 0x2000000000000000UL #define _RPAGE_SW1 0x00800 #define _RPAGE_SW2 0x00400 #define _RPAGE_SW3 0x00200 #define _RPAGE_RSV1 0x00040UL #define _RPAGE_PKEY_BIT4 0x1000000000000000UL #define _RPAGE_PKEY_BIT3 0x0800000000000000UL #define _RPAGE_PKEY_BIT2 0x0400000000000000UL #define _RPAGE_PKEY_BIT1 0x0200000000000000UL #define _RPAGE_PKEY_BIT0 0x0100000000000000UL #define _PAGE_PTE 0x4000000000000000UL /* distinguishes PTEs from pointers */ #define _PAGE_PRESENT 0x8000000000000000UL /* pte contains a translation */ /* * We need to mark a pmd pte invalid while splitting. We can do that by clearing * the _PAGE_PRESENT bit. But then that will be taken as a swap pte. In order to * differentiate between two use a SW field when invalidating. * * We do that temporary invalidate for regular pte entry in ptep_set_access_flags * * This is used only when _PAGE_PRESENT is cleared. */ #define _PAGE_INVALID _RPAGE_SW0 /* * Top and bottom bits of RPN which can be used by hash * translation mode, because we expect them to be zero * otherwise. */ #define _RPAGE_RPN0 0x01000 #define _RPAGE_RPN1 0x02000 #define _RPAGE_RPN43 0x0080000000000000UL #define _RPAGE_RPN42 0x0040000000000000UL #define _RPAGE_RPN41 0x0020000000000000UL /* Max physical address bit as per radix table */ #define _RPAGE_PA_MAX 56 /* * Max physical address bit we will use for now. * * This is mostly a hardware limitation and for now Power9 has * a 51 bit limit. * * This is different from the number of physical bit required to address * the last byte of memory. That is defined by MAX_PHYSMEM_BITS. * MAX_PHYSMEM_BITS is a linux limitation imposed by the maximum * number of sections we can support (SECTIONS_SHIFT). * * This is different from Radix page table limitation above and * should always be less than that. The limit is done such that * we can overload the bits between _RPAGE_PA_MAX and _PAGE_PA_MAX * for hash linux page table specific bits. * * In order to be compatible with future hardware generations we keep * some offsets and limit this for now to 53 */ #define _PAGE_PA_MAX 53 #define _PAGE_SOFT_DIRTY _RPAGE_SW3 /* software: software dirty tracking */ #define _PAGE_SPECIAL _RPAGE_SW2 /* software: special page */ #define _PAGE_DEVMAP _RPAGE_SW1 /* software: ZONE_DEVICE page */ /* * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE * Instead of fixing all of them, add an alternate define which * maps CI pte mapping. */ #define _PAGE_NO_CACHE _PAGE_TOLERANT /* * We support _RPAGE_PA_MAX bit real address in pte. On the linux side * we are limited by _PAGE_PA_MAX. Clear everything above _PAGE_PA_MAX * and every thing below PAGE_SHIFT; */ #define PTE_RPN_MASK (((1UL << _PAGE_PA_MAX) - 1) & (PAGE_MASK)) /* * set of bits not changed in pmd_modify. Even though we have hash specific bits * in here, on radix we expect them to be zero. */ #define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ _PAGE_ACCESSED | H_PAGE_THP_HUGE | _PAGE_PTE | \ _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) /* * user access blocked by key */ #define _PAGE_KERNEL_RW (_PAGE_PRIVILEGED | _PAGE_RW | _PAGE_DIRTY) #define _PAGE_KERNEL_RO (_PAGE_PRIVILEGED | _PAGE_READ) #define _PAGE_KERNEL_ROX (_PAGE_PRIVILEGED | _PAGE_READ | _PAGE_EXEC) #define _PAGE_KERNEL_RWX (_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) /* * _PAGE_CHG_MASK masks of bits that are to be preserved across * pgprot changes */ #define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \ _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) /* * We define 2 sets of base prot bits, one for basic pages (ie, * cacheable kernel and user pages) and one for non cacheable * pages. We always set _PAGE_COHERENT when SMP is enabled or * the processor might need it for DMA coherency. */ #define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) #define _PAGE_BASE (_PAGE_BASE_NC) /* Permission masks used to generate the __P and __S table, * * Note:__pgprot is defined in arch/powerpc/include/asm/page.h * * Write permissions imply read permissions for now (we could make write-only * pages on BookE but we don't bother for now). Execute permission control is * possible on platforms that define _PAGE_EXEC */ #define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_PRIVILEGED) #define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_RW) #define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_RW | _PAGE_EXEC) #define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_READ) #define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) #define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_READ) #define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) /* Radix only, Hash uses PAGE_READONLY_X + execute-only pkey instead */ #define PAGE_EXECONLY __pgprot(_PAGE_BASE | _PAGE_EXEC) /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) #define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_TOLERANT) #define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NON_IDEMPOTENT) #define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) #define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) #define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) #ifndef __ASSEMBLY__ /* * page table defines */ extern unsigned long __pte_index_size; extern unsigned long __pmd_index_size; extern unsigned long __pud_index_size; extern unsigned long __pgd_index_size; extern unsigned long __pud_cache_index; #define PTE_INDEX_SIZE __pte_index_size #define PMD_INDEX_SIZE __pmd_index_size #define PUD_INDEX_SIZE __pud_index_size #define PGD_INDEX_SIZE __pgd_index_size /* pmd table use page table fragments */ #define PMD_CACHE_INDEX 0 #define PUD_CACHE_INDEX __pud_cache_index /* * Because of use of pte fragments and THP, size of page table * are not always derived out of index size above. */ extern unsigned long __pte_table_size; extern unsigned long __pmd_table_size; extern unsigned long __pud_table_size; extern unsigned long __pgd_table_size; #define PTE_TABLE_SIZE __pte_table_size #define PMD_TABLE_SIZE __pmd_table_size #define PUD_TABLE_SIZE __pud_table_size #define PGD_TABLE_SIZE __pgd_table_size extern unsigned long __pmd_val_bits; extern unsigned long __pud_val_bits; extern unsigned long __pgd_val_bits; #define PMD_VAL_BITS __pmd_val_bits #define PUD_VAL_BITS __pud_val_bits #define PGD_VAL_BITS __pgd_val_bits extern unsigned long __pte_frag_nr; #define PTE_FRAG_NR __pte_frag_nr extern unsigned long __pte_frag_size_shift; #define PTE_FRAG_SIZE_SHIFT __pte_frag_size_shift #define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) extern unsigned long __pmd_frag_nr; #define PMD_FRAG_NR __pmd_frag_nr extern unsigned long __pmd_frag_size_shift; #define PMD_FRAG_SIZE_SHIFT __pmd_frag_size_shift #define PMD_FRAG_SIZE (1UL << PMD_FRAG_SIZE_SHIFT) #define PTRS_PER_PTE (1 << PTE_INDEX_SIZE) #define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) #define PTRS_PER_PUD (1 << PUD_INDEX_SIZE) #define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) #define MAX_PTRS_PER_PTE ((H_PTRS_PER_PTE > R_PTRS_PER_PTE) ? H_PTRS_PER_PTE : R_PTRS_PER_PTE) #define MAX_PTRS_PER_PMD ((H_PTRS_PER_PMD > R_PTRS_PER_PMD) ? H_PTRS_PER_PMD : R_PTRS_PER_PMD) #define MAX_PTRS_PER_PUD ((H_PTRS_PER_PUD > R_PTRS_PER_PUD) ? H_PTRS_PER_PUD : R_PTRS_PER_PUD) #define MAX_PTRS_PER_PGD (1 << (H_PGD_INDEX_SIZE > RADIX_PGD_INDEX_SIZE ? \ H_PGD_INDEX_SIZE : RADIX_PGD_INDEX_SIZE)) /* PMD_SHIFT determines what a second-level page table entry can map */ #define PMD_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE) #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) /* PUD_SHIFT determines what a third-level page table entry can map */ #define PUD_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) #define PUD_SIZE (1UL << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE-1)) /* PGDIR_SHIFT determines what a fourth-level page table entry can map */ #define PGDIR_SHIFT (PUD_SHIFT + PUD_INDEX_SIZE) #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) /* Bits to mask out from a PMD to get to the PTE page */ #define PMD_MASKED_BITS 0xc0000000000000ffUL /* Bits to mask out from a PUD to get to the PMD page */ #define PUD_MASKED_BITS 0xc0000000000000ffUL /* Bits to mask out from a PGD to get to the PUD page */ #define P4D_MASKED_BITS 0xc0000000000000ffUL /* * Used as an indicator for rcu callback functions */ enum pgtable_index { PTE_INDEX = 0, PMD_INDEX, PUD_INDEX, PGD_INDEX, /* * Below are used with 4k page size and hugetlb */ HTLB_16M_INDEX, HTLB_16G_INDEX, }; extern unsigned long __vmalloc_start; extern unsigned long __vmalloc_end; #define VMALLOC_START __vmalloc_start #define VMALLOC_END __vmalloc_end static inline unsigned int ioremap_max_order(void) { if (radix_enabled()) return PUD_SHIFT; return 7 + PAGE_SHIFT; /* default from linux/vmalloc.h */ } #define IOREMAP_MAX_ORDER ioremap_max_order() extern unsigned long __kernel_virt_start; extern unsigned long __kernel_io_start; extern unsigned long __kernel_io_end; #define KERN_VIRT_START __kernel_virt_start #define KERN_IO_START __kernel_io_start #define KERN_IO_END __kernel_io_end extern struct page *vmemmap; extern unsigned long pci_io_base; #endif /* __ASSEMBLY__ */ #include <asm/book3s/64/hash.h> #include <asm/book3s/64/radix.h> #if H_MAX_PHYSMEM_BITS > R_MAX_PHYSMEM_BITS #define MAX_PHYSMEM_BITS H_MAX_PHYSMEM_BITS #else #define MAX_PHYSMEM_BITS R_MAX_PHYSMEM_BITS #endif #ifdef CONFIG_PPC_64K_PAGES #include <asm/book3s/64/pgtable-64k.h> #else #include <asm/book3s/64/pgtable-4k.h> #endif #include <asm/barrier.h> /* * IO space itself carved into the PIO region (ISA and PHB IO space) and * the ioremap space * * ISA_IO_BASE = KERN_IO_START, 64K reserved area * PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE */ #define FULL_IO_SIZE 0x80000000ul #define ISA_IO_BASE (KERN_IO_START) #define ISA_IO_END (KERN_IO_START + 0x10000ul) #define PHB_IO_BASE (ISA_IO_END) #define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE) #define IOREMAP_BASE (PHB_IO_END) #define IOREMAP_START (ioremap_bot) #define IOREMAP_END (KERN_IO_END - FIXADDR_SIZE) #define FIXADDR_SIZE SZ_32M #ifndef __ASSEMBLY__ /* * This is the default implementation of various PTE accessors, it's * used in all cases except Book3S with 64K pages where we have a * concept of sub-pages */ #ifndef __real_pte #define __real_pte(e, p, o) ((real_pte_t){(e)}) #define __rpte_to_pte(r) ((r).pte) #define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT) #define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \ do { \ index = 0; \ shift = mmu_psize_defs[psize].shift; \ #define pte_iterate_hashed_end() } while(0) /* * We expect this to be called only for user addresses or kernel virtual * addresses other than the linear mapping. */ #define pte_pagesize_index(mm, addr, pte) MMU_PAGE_4K #endif /* __real_pte */ static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long clr, unsigned long set, int huge) { if (radix_enabled()) return radix__pte_update(mm, addr, ptep, clr, set, huge); return hash__pte_update(mm, addr, ptep, clr, set, huge); } /* * For hash even if we have _PAGE_ACCESSED = 0, we do a pte_update. * We currently remove entries from the hashtable regardless of whether * the entry was young or dirty. * * We should be more intelligent about this but for the moment we override * these functions and force a tlb flush unconditionally * For radix: H_PAGE_HASHPTE should be zero. Hence we can use the same * function for both hash and radix. */ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long old; if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) return 0; old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); return (old & _PAGE_ACCESSED) != 0; } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG #define ptep_test_and_clear_young(__vma, __addr, __ptep) \ ({ \ __ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep); \ }) /* * On Book3S CPUs, clearing the accessed bit without a TLB flush * doesn't cause data corruption. [ It could cause incorrect * page aging and the (mistaken) reclaim of hot pages, but the * chance of that should be relatively low. ] * * So as a performance optimization don't flush the TLB when * clearing the accessed bit, it will eventually be flushed by * a context switch or a VM operation anyway. [ In the rare * event of it not getting flushed for a long time the delay * shouldn't really matter because there's no real memory * pressure for swapout to react to. ] * * Note: this optimisation also exists in pte_needs_flush() and * huge_pmd_needs_flush(). */ #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young ptep_test_and_clear_young #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH #define pmdp_clear_flush_young pmdp_test_and_clear_young static inline int pte_write(pte_t pte) { return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE)); } static inline int pte_read(pte_t pte) { return !!(pte_raw(pte) & cpu_to_be64(_PAGE_READ)); } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { if (pte_write(*ptep)) pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0); } #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { if (pte_write(*ptep)) pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1); } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); return __pte(old); } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) { if (full && radix_enabled()) { /* * We know that this is a full mm pte clear and * hence can be sure there is no parallel set_pte. */ return radix__ptep_get_and_clear_full(mm, addr, ptep, full); } return ptep_get_and_clear(mm, addr, ptep); } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t * ptep) { pte_update(mm, addr, ptep, ~0UL, 0, 0); } static inline int pte_dirty(pte_t pte) { return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY)); } static inline int pte_young(pte_t pte) { return !!(pte_raw(pte) & cpu_to_be64(_PAGE_ACCESSED)); } static inline int pte_special(pte_t pte) { return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SPECIAL)); } static inline bool pte_exec(pte_t pte) { return !!(pte_raw(pte) & cpu_to_be64(_PAGE_EXEC)); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline bool pte_soft_dirty(pte_t pte) { return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SOFT_DIRTY)); } static inline pte_t pte_mksoft_dirty(pte_t pte) { return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SOFT_DIRTY)); } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SOFT_DIRTY)); } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ #ifdef CONFIG_NUMA_BALANCING static inline int pte_protnone(pte_t pte) { return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE | _PAGE_RWX)) == cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE); } #endif /* CONFIG_NUMA_BALANCING */ static inline bool pte_hw_valid(pte_t pte) { return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE)) == cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE); } static inline int pte_present(pte_t pte) { /* * A pte is considerent present if _PAGE_PRESENT is set. * We also need to consider the pte present which is marked * invalid during ptep_set_access_flags. Hence we look for _PAGE_INVALID * if we find _PAGE_PRESENT cleared. */ if (pte_hw_valid(pte)) return true; return (pte_raw(pte) & cpu_to_be64(_PAGE_INVALID | _PAGE_PTE)) == cpu_to_be64(_PAGE_INVALID | _PAGE_PTE); } #ifdef CONFIG_PPC_MEM_KEYS extern bool arch_pte_access_permitted(u64 pte, bool write, bool execute); #else static inline bool arch_pte_access_permitted(u64 pte, bool write, bool execute) { return true; } #endif /* CONFIG_PPC_MEM_KEYS */ static inline bool pte_user(pte_t pte) { return !(pte_raw(pte) & cpu_to_be64(_PAGE_PRIVILEGED)); } #define pte_access_permitted pte_access_permitted static inline bool pte_access_permitted(pte_t pte, bool write) { /* * _PAGE_READ is needed for any access and will be * cleared for PROT_NONE */ if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) return false; if (write && !pte_write(pte)) return false; return arch_pte_access_permitted(pte_val(pte), write, 0); } /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * * Even if PTEs can be unsigned long long, a PFN is always an unsigned * long for now. */ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot) { VM_BUG_ON(pfn >> (64 - PAGE_SHIFT)); VM_BUG_ON((pfn << PAGE_SHIFT) & ~PTE_RPN_MASK); return __pte(((pte_basic_t)pfn << PAGE_SHIFT) | pgprot_val(pgprot) | _PAGE_PTE); } static inline unsigned long pte_pfn(pte_t pte) { return (pte_val(pte) & PTE_RPN_MASK) >> PAGE_SHIFT; } /* Generic modifiers for PTE bits */ static inline pte_t pte_wrprotect(pte_t pte) { return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE)); } static inline pte_t pte_exprotect(pte_t pte) { return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_EXEC)); } static inline pte_t pte_mkclean(pte_t pte) { return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_DIRTY)); } static inline pte_t pte_mkold(pte_t pte) { return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_ACCESSED)); } static inline pte_t pte_mkexec(pte_t pte) { return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_EXEC)); } static inline pte_t pte_mkwrite(pte_t pte) { /* * write implies read, hence set both */ return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_RW)); } static inline pte_t pte_mkdirty(pte_t pte) { return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_DIRTY | _PAGE_SOFT_DIRTY)); } static inline pte_t pte_mkyoung(pte_t pte) { return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_ACCESSED)); } static inline pte_t pte_mkspecial(pte_t pte) { return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL)); } static inline pte_t pte_mkhuge(pte_t pte) { return pte; } static inline pte_t pte_mkdevmap(pte_t pte) { return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL | _PAGE_DEVMAP)); } static inline pte_t pte_mkprivileged(pte_t pte) { return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED)); } static inline pte_t pte_mkuser(pte_t pte) { return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED)); } /* * This is potentially called with a pmd as the argument, in which case it's not * safe to check _PAGE_DEVMAP unless we also confirm that _PAGE_PTE is set. * That's because the bit we use for _PAGE_DEVMAP is not reserved for software * use in page directory entries (ie. non-ptes). */ static inline int pte_devmap(pte_t pte) { u64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE); return (pte_raw(pte) & mask) == mask; } static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { /* FIXME!! check whether this need to be a conditional */ return __pte_raw((pte_raw(pte) & cpu_to_be64(_PAGE_CHG_MASK)) | cpu_to_be64(pgprot_val(newprot))); } /* Encode and de-code a swap entry */ #define MAX_SWAPFILES_CHECK() do { \ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \ /* \ * Don't have overlapping bits with _PAGE_HPTEFLAGS \ * We filter HPTEFLAGS on set_pte. \ */ \ BUILD_BUG_ON(_PAGE_HPTEFLAGS & SWP_TYPE_MASK); \ BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY); \ BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_EXCLUSIVE); \ } while (0) #define SWP_TYPE_BITS 5 #define SWP_TYPE_MASK ((1UL << SWP_TYPE_BITS) - 1) #define __swp_type(x) ((x).val & SWP_TYPE_MASK) #define __swp_offset(x) (((x).val & PTE_RPN_MASK) >> PAGE_SHIFT) #define __swp_entry(type, offset) ((swp_entry_t) { \ (type) | (((offset) << PAGE_SHIFT) & PTE_RPN_MASK)}) /* * swp_entry_t must be independent of pte bits. We build a swp_entry_t from * swap type and offset we get from swap and convert that to pte to find a * matching pte in linux page table. * Clear bits not found in swap entries here. */ #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) & ~_PAGE_PTE }) #define __swp_entry_to_pte(x) __pte((x).val | _PAGE_PTE) #define __pmd_to_swp_entry(pmd) (__pte_to_swp_entry(pmd_pte(pmd))) #define __swp_entry_to_pmd(x) (pte_pmd(__swp_entry_to_pte(x))) #ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SWP_SOFT_DIRTY _PAGE_SOFT_DIRTY #else #define _PAGE_SWP_SOFT_DIRTY 0UL #endif /* CONFIG_MEM_SOFT_DIRTY */ #define _PAGE_SWP_EXCLUSIVE _PAGE_NON_IDEMPOTENT #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_SOFT_DIRTY)); } static inline bool pte_swp_soft_dirty(pte_t pte) { return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_SOFT_DIRTY)); } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SWP_SOFT_DIRTY)); } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ #define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline pte_t pte_swp_mkexclusive(pte_t pte) { return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_EXCLUSIVE)); } static inline int pte_swp_exclusive(pte_t pte) { return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_EXCLUSIVE)); } static inline pte_t pte_swp_clear_exclusive(pte_t pte) { return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SWP_EXCLUSIVE)); } static inline bool check_pte_access(unsigned long access, unsigned long ptev) { /* * This check for _PAGE_RWX and _PAGE_PRESENT bits */ if (access & ~ptev) return false; /* * This check for access to privilege space */ if ((access & _PAGE_PRIVILEGED) != (ptev & _PAGE_PRIVILEGED)) return false; return true; } /* * Generic functions with hash/radix callbacks */ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, int psize) { if (radix_enabled()) return radix__ptep_set_access_flags(vma, ptep, entry, address, psize); return hash__ptep_set_access_flags(ptep, entry); } #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { if (radix_enabled()) return radix__pte_same(pte_a, pte_b); return hash__pte_same(pte_a, pte_b); } static inline int pte_none(pte_t pte) { if (radix_enabled()) return radix__pte_none(pte); return hash__pte_none(pte); } static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, int percpu) { VM_WARN_ON(!(pte_raw(pte) & cpu_to_be64(_PAGE_PTE))); /* * Keep the _PAGE_PTE added till we are sure we handle _PAGE_PTE * in all the callers. */ pte = __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PTE)); if (radix_enabled()) return radix__set_pte_at(mm, addr, ptep, pte, percpu); return hash__set_pte_at(mm, addr, ptep, pte, percpu); } #define _PAGE_CACHE_CTL (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT) #define pgprot_noncached pgprot_noncached static inline pgprot_t pgprot_noncached(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | _PAGE_NON_IDEMPOTENT); } #define pgprot_noncached_wc pgprot_noncached_wc static inline pgprot_t pgprot_noncached_wc(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | _PAGE_TOLERANT); } #define pgprot_cached pgprot_cached static inline pgprot_t pgprot_cached(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL)); } #define pgprot_writecombine pgprot_writecombine static inline pgprot_t pgprot_writecombine(pgprot_t prot) { return pgprot_noncached_wc(prot); } /* * check a pte mapping have cache inhibited property */ static inline bool pte_ci(pte_t pte) { __be64 pte_v = pte_raw(pte); if (((pte_v & cpu_to_be64(_PAGE_CACHE_CTL)) == cpu_to_be64(_PAGE_TOLERANT)) || ((pte_v & cpu_to_be64(_PAGE_CACHE_CTL)) == cpu_to_be64(_PAGE_NON_IDEMPOTENT))) return true; return false; } static inline void pmd_clear(pmd_t *pmdp) { if (IS_ENABLED(CONFIG_DEBUG_VM) && !radix_enabled()) { /* * Don't use this if we can possibly have a hash page table * entry mapping this. */ WARN_ON((pmd_val(*pmdp) & (H_PAGE_HASHPTE | _PAGE_PTE)) == (H_PAGE_HASHPTE | _PAGE_PTE)); } *pmdp = __pmd(0); } static inline int pmd_none(pmd_t pmd) { return !pmd_raw(pmd); } static inline int pmd_present(pmd_t pmd) { /* * A pmd is considerent present if _PAGE_PRESENT is set. * We also need to consider the pmd present which is marked * invalid during a split. Hence we look for _PAGE_INVALID * if we find _PAGE_PRESENT cleared. */ if (pmd_raw(pmd) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID)) return true; return false; } static inline int pmd_is_serializing(pmd_t pmd) { /* * If the pmd is undergoing a split, the _PAGE_PRESENT bit is clear * and _PAGE_INVALID is set (see pmd_present, pmdp_invalidate). * * This condition may also occur when flushing a pmd while flushing * it (see ptep_modify_prot_start), so callers must ensure this * case is fine as well. */ if ((pmd_raw(pmd) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID)) == cpu_to_be64(_PAGE_INVALID)) return true; return false; } static inline int pmd_bad(pmd_t pmd) { if (radix_enabled()) return radix__pmd_bad(pmd); return hash__pmd_bad(pmd); } static inline void pud_clear(pud_t *pudp) { if (IS_ENABLED(CONFIG_DEBUG_VM) && !radix_enabled()) { /* * Don't use this if we can possibly have a hash page table * entry mapping this. */ WARN_ON((pud_val(*pudp) & (H_PAGE_HASHPTE | _PAGE_PTE)) == (H_PAGE_HASHPTE | _PAGE_PTE)); } *pudp = __pud(0); } static inline int pud_none(pud_t pud) { return !pud_raw(pud); } static inline int pud_present(pud_t pud) { return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); } extern struct page *pud_page(pud_t pud); extern struct page *pmd_page(pmd_t pmd); static inline pte_t pud_pte(pud_t pud) { return __pte_raw(pud_raw(pud)); } static inline pud_t pte_pud(pte_t pte) { return __pud_raw(pte_raw(pte)); } #define pud_write(pud) pte_write(pud_pte(pud)) static inline int pud_bad(pud_t pud) { if (radix_enabled()) return radix__pud_bad(pud); return hash__pud_bad(pud); } #define pud_access_permitted pud_access_permitted static inline bool pud_access_permitted(pud_t pud, bool write) { return pte_access_permitted(pud_pte(pud), write); } #define __p4d_raw(x) ((p4d_t) { __pgd_raw(x) }) static inline __be64 p4d_raw(p4d_t x) { return pgd_raw(x.pgd); } #define p4d_write(p4d) pte_write(p4d_pte(p4d)) static inline void p4d_clear(p4d_t *p4dp) { *p4dp = __p4d(0); } static inline int p4d_none(p4d_t p4d) { return !p4d_raw(p4d); } static inline int p4d_present(p4d_t p4d) { return !!(p4d_raw(p4d) & cpu_to_be64(_PAGE_PRESENT)); } static inline pte_t p4d_pte(p4d_t p4d) { return __pte_raw(p4d_raw(p4d)); } static inline p4d_t pte_p4d(pte_t pte) { return __p4d_raw(pte_raw(pte)); } static inline int p4d_bad(p4d_t p4d) { if (radix_enabled()) return radix__p4d_bad(p4d); return hash__p4d_bad(p4d); } #define p4d_access_permitted p4d_access_permitted static inline bool p4d_access_permitted(p4d_t p4d, bool write) { return pte_access_permitted(p4d_pte(p4d), write); } extern struct page *p4d_page(p4d_t p4d); /* Pointers in the page table tree are physical addresses */ #define __pgtable_ptr_val(ptr) __pa(ptr) static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_val(p4d) & ~P4D_MASKED_BITS); } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_val(pud) & ~PUD_MASKED_BITS); } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) static inline int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot) { if (radix_enabled()) { #if defined(CONFIG_PPC_RADIX_MMU) && defined(DEBUG_VM) unsigned long page_size = 1 << mmu_psize_defs[mmu_io_psize].shift; WARN((page_size != PAGE_SIZE), "I/O page size != PAGE_SIZE"); #endif return radix__map_kernel_page(ea, pa, prot, PAGE_SIZE); } return hash__map_kernel_page(ea, pa, prot); } void unmap_kernel_page(unsigned long va); static inline int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys) { if (radix_enabled()) return radix__vmemmap_create_mapping(start, page_size, phys); return hash__vmemmap_create_mapping(start, page_size, phys); } #ifdef CONFIG_MEMORY_HOTPLUG static inline void vmemmap_remove_mapping(unsigned long start, unsigned long page_size) { if (radix_enabled()) return radix__vmemmap_remove_mapping(start, page_size); return hash__vmemmap_remove_mapping(start, page_size); } #endif #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) static inline void __kernel_map_pages(struct page *page, int numpages, int enable) { if (radix_enabled()) radix__kernel_map_pages(page, numpages, enable); else hash__kernel_map_pages(page, numpages, enable); } #endif static inline pte_t pmd_pte(pmd_t pmd) { return __pte_raw(pmd_raw(pmd)); } static inline pmd_t pte_pmd(pte_t pte) { return __pmd_raw(pte_raw(pte)); } static inline pte_t *pmdp_ptep(pmd_t *pmd) { return (pte_t *)pmd; } #define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd)) #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #define pmd_soft_dirty(pmd) pte_soft_dirty(pmd_pte(pmd)) #define pmd_mksoft_dirty(pmd) pte_pmd(pte_mksoft_dirty(pmd_pte(pmd))) #define pmd_clear_soft_dirty(pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd))) #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION #define pmd_swp_mksoft_dirty(pmd) pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd))) #define pmd_swp_soft_dirty(pmd) pte_swp_soft_dirty(pmd_pte(pmd)) #define pmd_swp_clear_soft_dirty(pmd) pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd))) #endif #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ #ifdef CONFIG_NUMA_BALANCING static inline int pmd_protnone(pmd_t pmd) { return pte_protnone(pmd_pte(pmd)); } #endif /* CONFIG_NUMA_BALANCING */ #define pmd_write(pmd) pte_write(pmd_pte(pmd)) #define pmd_access_permitted pmd_access_permitted static inline bool pmd_access_permitted(pmd_t pmd, bool write) { /* * pmdp_invalidate sets this combination (which is not caught by * !pte_present() check in pte_access_permitted), to prevent * lock-free lookups, as part of the serialize_against_pte_lookup() * synchronisation. * * This also catches the case where the PTE's hardware PRESENT bit is * cleared while TLB is flushed, which is suboptimal but should not * be frequent. */ if (pmd_is_serializing(pmd)) return false; return pte_access_permitted(pmd_pte(pmd), write); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot); extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } extern int hash__has_transparent_hugepage(void); static inline int has_transparent_hugepage(void) { if (radix_enabled()) return radix__has_transparent_hugepage(); return hash__has_transparent_hugepage(); } #define has_transparent_hugepage has_transparent_hugepage static inline unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, unsigned long clr, unsigned long set) { if (radix_enabled()) return radix__pmd_hugepage_update(mm, addr, pmdp, clr, set); return hash__pmd_hugepage_update(mm, addr, pmdp, clr, set); } /* * returns true for pmd migration entries, THP, devmap, hugetlb * But compile time dependent on THP config */ static inline int pmd_large(pmd_t pmd) { return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); } /* * For radix we should always find H_PAGE_HASHPTE zero. Hence * the below will work for radix too */ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { unsigned long old; if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0) return 0; old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0); return ((old & _PAGE_ACCESSED) != 0); } #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { if (pmd_write(*pmdp)) pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0); } /* * Only returns true for a THP. False for pmd migration entry. * We also need to return true when we come across a pte that * in between a thp split. While splitting THP, we mark the pmd * invalid (pmdp_invalidate()) before we set it with pte page * address. A pmd_trans_huge() check against a pmd entry during that time * should return true. * We should not call this on a hugetlb entry. We should check for HugeTLB * entry using vma->vm_flags * The page table walk rule is explained in Documentation/mm/transhuge.rst */ static inline int pmd_trans_huge(pmd_t pmd) { if (!pmd_present(pmd)) return false; if (radix_enabled()) return radix__pmd_trans_huge(pmd); return hash__pmd_trans_huge(pmd); } #define __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { if (radix_enabled()) return radix__pmd_same(pmd_a, pmd_b); return hash__pmd_same(pmd_a, pmd_b); } static inline pmd_t __pmd_mkhuge(pmd_t pmd) { if (radix_enabled()) return radix__pmd_mkhuge(pmd); return hash__pmd_mkhuge(pmd); } /* * pfn_pmd return a pmd_t that can be used as pmd pte entry. */ static inline pmd_t pmd_mkhuge(pmd_t pmd) { #ifdef CONFIG_DEBUG_VM if (radix_enabled()) WARN_ON((pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)) == 0); else WARN_ON((pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE | H_PAGE_THP_HUGE)) != cpu_to_be64(_PAGE_PTE | H_PAGE_THP_HUGE)); #endif return pmd; } #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { if (radix_enabled()) return radix__pmdp_huge_get_and_clear(mm, addr, pmdp); return hash__pmdp_huge_get_and_clear(mm, addr, pmdp); } static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { if (radix_enabled()) return radix__pmdp_collapse_flush(vma, address, pmdp); return hash__pmdp_collapse_flush(vma, address, pmdp); } #define pmdp_collapse_flush pmdp_collapse_flush #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, int full); #define __HAVE_ARCH_PGTABLE_DEPOSIT static inline void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) { if (radix_enabled()) return radix__pgtable_trans_huge_deposit(mm, pmdp, pgtable); return hash__pgtable_trans_huge_deposit(mm, pmdp, pgtable); } #define __HAVE_ARCH_PGTABLE_WITHDRAW static inline pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { if (radix_enabled()) return radix__pgtable_trans_huge_withdraw(mm, pmdp); return hash__pgtable_trans_huge_withdraw(mm, pmdp); } #define __HAVE_ARCH_PMDP_INVALIDATE extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define pmd_move_must_withdraw pmd_move_must_withdraw struct spinlock; extern int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, struct spinlock *old_pmd_ptl, struct vm_area_struct *vma); /* * Hash translation mode use the deposited table to store hash pte * slot information. */ #define arch_needs_pgtable_deposit arch_needs_pgtable_deposit static inline bool arch_needs_pgtable_deposit(void) { if (radix_enabled()) return false; return true; } extern void serialize_against_pte_lookup(struct mm_struct *mm); static inline pmd_t pmd_mkdevmap(pmd_t pmd) { if (radix_enabled()) return radix__pmd_mkdevmap(pmd); return hash__pmd_mkdevmap(pmd); } static inline int pmd_devmap(pmd_t pmd) { return pte_devmap(pmd_pte(pmd)); } static inline int pud_devmap(pud_t pud) { return 0; } static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline int pud_pfn(pud_t pud) { /* * Currently all calls to pud_pfn() are gated around a pud_devmap() * check so this should never be used. If it grows another user we * want to know about it. */ BUILD_BUG(); return 0; } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *); void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, pte_t *, pte_t, pte_t); /* * Returns true for a R -> RW upgrade of pte */ static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_val) { if (!(old_val & _PAGE_READ)) return false; if ((!(old_val & _PAGE_WRITE)) && (new_val & _PAGE_WRITE)) return true; return false; } /* * Like pmd_huge() and pmd_large(), but works regardless of config options */ #define pmd_is_leaf pmd_is_leaf #define pmd_leaf pmd_is_leaf static inline bool pmd_is_leaf(pmd_t pmd) { return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); } #define pud_is_leaf pud_is_leaf #define pud_leaf pud_is_leaf static inline bool pud_is_leaf(pud_t pud) { return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); } #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */ |