1// SPDX-License-Identifier: GPL-2.0-only 2/* 3 * Copyright 2002 Andi Kleen, SuSE Labs. 4 * Thanks to Ben LaHaise for precious feedback. 5 */ 6#include <linux/highmem.h> 7#include <linux/memblock.h> 8#include <linux/sched.h> 9#include <linux/mm.h> 10#include <linux/interrupt.h> 11#include <linux/seq_file.h> 12#include <linux/debugfs.h> 13#include <linux/pfn.h> 14#include <linux/percpu.h> 15#include <linux/gfp.h> 16#include <linux/pci.h> 17#include <linux/vmalloc.h> 18#include <linux/libnvdimm.h> 19 20#include <asm/e820/api.h> 21#include <asm/processor.h> 22#include <asm/tlbflush.h> 23#include <asm/sections.h> 24#include <asm/setup.h> 25#include <linux/uaccess.h> 26#include <asm/pgalloc.h> 27#include <asm/proto.h> 28#include <asm/memtype.h> 29#include <asm/set_memory.h> 30 31#include "../mm_internal.h" 32 33/* 34 * The current flushing context - we pass it instead of 5 arguments: 35 */ 36struct cpa_data { 37 unsigned long *vaddr; 38 pgd_t *pgd; 39 pgprot_t mask_set; 40 pgprot_t mask_clr; 41 unsigned long numpages; 42 unsigned long curpage; 43 unsigned long pfn; 44 unsigned int flags; 45 unsigned int force_split : 1, 46 force_static_prot : 1, 47 force_flush_all : 1; 48 struct page **pages; 49}; 50 51enum cpa_warn { 52 CPA_CONFLICT, 53 CPA_PROTECT, 54 CPA_DETECT, 55}; 56 57static const int cpa_warn_level = CPA_PROTECT; 58 59/* 60 * Serialize cpa() (for !DEBUG_PAGEALLOC which uses large identity mappings) 61 * using cpa_lock. So that we don't allow any other cpu, with stale large tlb 62 * entries change the page attribute in parallel to some other cpu 63 * splitting a large page entry along with changing the attribute. 64 */ 65static DEFINE_SPINLOCK(cpa_lock); 66 67#define CPA_FLUSHTLB 1 68#define CPA_ARRAY 2 69#define CPA_PAGES_ARRAY 4 70#define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */ 71 72static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm) 73{ 74 return __pgprot(cachemode2protval(pcm)); 75} 76 77#ifdef CONFIG_PROC_FS 78static unsigned long direct_pages_count[PG_LEVEL_NUM]; 79 80void update_page_count(int level, unsigned long pages) 81{ 82 /* Protect against CPA */ 83 spin_lock(&pgd_lock); 84 direct_pages_count[level] += pages; 85 spin_unlock(&pgd_lock); 86} 87 88static void split_page_count(int level) 89{ 90 if (direct_pages_count[level] == 0) 91 return; 92 93 direct_pages_count[level]--; 94 direct_pages_count[level - 1] += PTRS_PER_PTE; 95} 96 97void arch_report_meminfo(struct seq_file *m) 98{ 99 seq_printf(m, "DirectMap4k: %8lu kB\n", 100 direct_pages_count[PG_LEVEL_4K] << 2); 101#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) 102 seq_printf(m, "DirectMap2M: %8lu kB\n", 103 direct_pages_count[PG_LEVEL_2M] << 11); 104#else 105 seq_printf(m, "DirectMap4M: %8lu kB\n", 106 direct_pages_count[PG_LEVEL_2M] << 12); 107#endif 108 if (direct_gbpages) 109 seq_printf(m, "DirectMap1G: %8lu kB\n", 110 direct_pages_count[PG_LEVEL_1G] << 20); 111} 112#else 113static inline void split_page_count(int level) { } 114#endif 115 116#ifdef CONFIG_X86_CPA_STATISTICS 117 118static unsigned long cpa_1g_checked; 119static unsigned long cpa_1g_sameprot; 120static unsigned long cpa_1g_preserved; 121static unsigned long cpa_2m_checked; 122static unsigned long cpa_2m_sameprot; 123static unsigned long cpa_2m_preserved; 124static unsigned long cpa_4k_install; 125 126static inline void cpa_inc_1g_checked(void) 127{ 128 cpa_1g_checked++; 129} 130 131static inline void cpa_inc_2m_checked(void) 132{ 133 cpa_2m_checked++; 134} 135 136static inline void cpa_inc_4k_install(void) 137{ 138 data_race(cpa_4k_install++); 139} 140 141static inline void cpa_inc_lp_sameprot(int level) 142{ 143 if (level == PG_LEVEL_1G) 144 cpa_1g_sameprot++; 145 else 146 cpa_2m_sameprot++; 147} 148 149static inline void cpa_inc_lp_preserved(int level) 150{ 151 if (level == PG_LEVEL_1G) 152 cpa_1g_preserved++; 153 else 154 cpa_2m_preserved++; 155} 156 157static int cpastats_show(struct seq_file *m, void *p) 158{ 159 seq_printf(m, "1G pages checked: %16lu\n", cpa_1g_checked); 160 seq_printf(m, "1G pages sameprot: %16lu\n", cpa_1g_sameprot); 161 seq_printf(m, "1G pages preserved: %16lu\n", cpa_1g_preserved); 162 seq_printf(m, "2M pages checked: %16lu\n", cpa_2m_checked); 163 seq_printf(m, "2M pages sameprot: %16lu\n", cpa_2m_sameprot); 164 seq_printf(m, "2M pages preserved: %16lu\n", cpa_2m_preserved); 165 seq_printf(m, "4K pages set-checked: %16lu\n", cpa_4k_install); 166 return 0; 167} 168 169static int cpastats_open(struct inode *inode, struct file *file) 170{ 171 return single_open(file, cpastats_show, NULL); 172} 173 174static const struct file_operations cpastats_fops = { 175 .open = cpastats_open, 176 .read = seq_read, 177 .llseek = seq_lseek, 178 .release = single_release, 179}; 180 181static int __init cpa_stats_init(void) 182{ 183 debugfs_create_file("cpa_stats", S_IRUSR, arch_debugfs_dir, NULL, 184 &cpastats_fops); 185 return 0; 186} 187late_initcall(cpa_stats_init); 188#else 189static inline void cpa_inc_1g_checked(void) { } 190static inline void cpa_inc_2m_checked(void) { } 191static inline void cpa_inc_4k_install(void) { } 192static inline void cpa_inc_lp_sameprot(int level) { } 193static inline void cpa_inc_lp_preserved(int level) { } 194#endif 195 196 197static inline int 198within(unsigned long addr, unsigned long start, unsigned long end) 199{ 200 return addr >= start && addr < end; 201} 202 203static inline int 204within_inclusive(unsigned long addr, unsigned long start, unsigned long end) 205{ 206 return addr >= start && addr <= end; 207} 208 209#ifdef CONFIG_X86_64 210 211static inline unsigned long highmap_start_pfn(void) 212{ 213 return __pa_symbol(_text) >> PAGE_SHIFT; 214} 215 216static inline unsigned long highmap_end_pfn(void) 217{ 218 /* Do not reference physical address outside the kernel. */ 219 return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT; 220} 221 222static bool __cpa_pfn_in_highmap(unsigned long pfn) 223{ 224 /* 225 * Kernel text has an alias mapping at a high address, known 226 * here as "highmap". 227 */ 228 return within_inclusive(pfn, highmap_start_pfn(), highmap_end_pfn()); 229} 230 231#else 232 233static bool __cpa_pfn_in_highmap(unsigned long pfn) 234{ 235 /* There is no highmap on 32-bit */ 236 return false; 237} 238 239#endif 240 241/* 242 * See set_mce_nospec(). 243 * 244 * Machine check recovery code needs to change cache mode of poisoned pages to 245 * UC to avoid speculative access logging another error. But passing the 246 * address of the 1:1 mapping to set_memory_uc() is a fine way to encourage a 247 * speculative access. So we cheat and flip the top bit of the address. This 248 * works fine for the code that updates the page tables. But at the end of the 249 * process we need to flush the TLB and cache and the non-canonical address 250 * causes a #GP fault when used by the INVLPG and CLFLUSH instructions. 251 * 252 * But in the common case we already have a canonical address. This code 253 * will fix the top bit if needed and is a no-op otherwise. 254 */ 255static inline unsigned long fix_addr(unsigned long addr) 256{ 257#ifdef CONFIG_X86_64 258 return (long)(addr << 1) >> 1; 259#else 260 return addr; 261#endif 262} 263 264static unsigned long __cpa_addr(struct cpa_data *cpa, unsigned long idx) 265{ 266 if (cpa->flags & CPA_PAGES_ARRAY) { 267 struct page *page = cpa->pages[idx]; 268 269 if (unlikely(PageHighMem(page))) 270 return 0; 271 272 return (unsigned long)page_address(page); 273 } 274 275 if (cpa->flags & CPA_ARRAY) 276 return cpa->vaddr[idx]; 277 278 return *cpa->vaddr + idx * PAGE_SIZE; 279} 280 281/* 282 * Flushing functions 283 */ 284 285static void clflush_cache_range_opt(void *vaddr, unsigned int size) 286{ 287 const unsigned long clflush_size = boot_cpu_data.x86_clflush_size; 288 void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1)); 289 void *vend = vaddr + size; 290 291 if (p >= vend) 292 return; 293 294 for (; p < vend; p += clflush_size) 295 clflushopt(p); 296} 297 298/** 299 * clflush_cache_range - flush a cache range with clflush 300 * @vaddr: virtual start address 301 * @size: number of bytes to flush 302 * 303 * CLFLUSHOPT is an unordered instruction which needs fencing with MFENCE or 304 * SFENCE to avoid ordering issues. 305 */ 306void clflush_cache_range(void *vaddr, unsigned int size) 307{ 308 mb(); 309 clflush_cache_range_opt(vaddr, size); 310 mb(); 311} 312EXPORT_SYMBOL_GPL(clflush_cache_range); 313 314#ifdef CONFIG_ARCH_HAS_PMEM_API 315void arch_invalidate_pmem(void *addr, size_t size) 316{ 317 clflush_cache_range(addr, size); 318} 319EXPORT_SYMBOL_GPL(arch_invalidate_pmem); 320#endif 321 322static void __cpa_flush_all(void *arg) 323{ 324 unsigned long cache = (unsigned long)arg; 325 326 /* 327 * Flush all to work around Errata in early athlons regarding 328 * large page flushing. 329 */ 330 __flush_tlb_all(); 331 332 if (cache && boot_cpu_data.x86 >= 4) 333 wbinvd(); 334} 335 336static void cpa_flush_all(unsigned long cache) 337{ 338 BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); 339 340 on_each_cpu(__cpa_flush_all, (void *) cache, 1); 341} 342 343static void __cpa_flush_tlb(void *data) 344{ 345 struct cpa_data *cpa = data; 346 unsigned int i; 347 348 for (i = 0; i < cpa->numpages; i++) 349 flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i))); 350} 351 352static void cpa_flush(struct cpa_data *data, int cache) 353{ 354 struct cpa_data *cpa = data; 355 unsigned int i; 356 357 BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); 358 359 if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) { 360 cpa_flush_all(cache); 361 return; 362 } 363 364 if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling) 365 flush_tlb_all(); 366 else 367 on_each_cpu(__cpa_flush_tlb, cpa, 1); 368 369 if (!cache) 370 return; 371 372 mb(); 373 for (i = 0; i < cpa->numpages; i++) { 374 unsigned long addr = __cpa_addr(cpa, i); 375 unsigned int level; 376 377 pte_t *pte = lookup_address(addr, &level); 378 379 /* 380 * Only flush present addresses: 381 */ 382 if (pte && (pte_val(*pte) & _PAGE_PRESENT)) 383 clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE); 384 } 385 mb(); 386} 387 388static bool overlaps(unsigned long r1_start, unsigned long r1_end, 389 unsigned long r2_start, unsigned long r2_end) 390{ 391 return (r1_start <= r2_end && r1_end >= r2_start) || 392 (r2_start <= r1_end && r2_end >= r1_start); 393} 394 395#ifdef CONFIG_PCI_BIOS 396/* 397 * The BIOS area between 640k and 1Mb needs to be executable for PCI BIOS 398 * based config access (CONFIG_PCI_GOBIOS) support. 399 */ 400#define BIOS_PFN PFN_DOWN(BIOS_BEGIN) 401#define BIOS_PFN_END PFN_DOWN(BIOS_END - 1) 402 403static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn) 404{ 405 if (pcibios_enabled && overlaps(spfn, epfn, BIOS_PFN, BIOS_PFN_END)) 406 return _PAGE_NX; 407 return 0; 408} 409#else 410static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn) 411{ 412 return 0; 413} 414#endif 415 416/* 417 * The .rodata section needs to be read-only. Using the pfn catches all 418 * aliases. This also includes __ro_after_init, so do not enforce until 419 * kernel_set_to_readonly is true. 420 */ 421static pgprotval_t protect_rodata(unsigned long spfn, unsigned long epfn) 422{ 423 unsigned long epfn_ro, spfn_ro = PFN_DOWN(__pa_symbol(__start_rodata)); 424 425 /* 426 * Note: __end_rodata is at page aligned and not inclusive, so 427 * subtract 1 to get the last enforced PFN in the rodata area. 428 */ 429 epfn_ro = PFN_DOWN(__pa_symbol(__end_rodata)) - 1; 430 431 if (kernel_set_to_readonly && overlaps(spfn, epfn, spfn_ro, epfn_ro)) 432 return _PAGE_RW; 433 return 0; 434} 435 436/* 437 * Protect kernel text against becoming non executable by forbidding 438 * _PAGE_NX. This protects only the high kernel mapping (_text -> _etext) 439 * out of which the kernel actually executes. Do not protect the low 440 * mapping. 441 * 442 * This does not cover __inittext since that is gone after boot. 443 */ 444static pgprotval_t protect_kernel_text(unsigned long start, unsigned long end) 445{ 446 unsigned long t_end = (unsigned long)_etext - 1; 447 unsigned long t_start = (unsigned long)_text; 448 449 if (overlaps(start, end, t_start, t_end)) 450 return _PAGE_NX; 451 return 0; 452} 453 454#if defined(CONFIG_X86_64) 455/* 456 * Once the kernel maps the text as RO (kernel_set_to_readonly is set), 457 * kernel text mappings for the large page aligned text, rodata sections 458 * will be always read-only. For the kernel identity mappings covering the 459 * holes caused by this alignment can be anything that user asks. 460 * 461 * This will preserve the large page mappings for kernel text/data at no 462 * extra cost. 463 */ 464static pgprotval_t protect_kernel_text_ro(unsigned long start, 465 unsigned long end) 466{ 467 unsigned long t_end = (unsigned long)__end_rodata_hpage_align - 1; 468 unsigned long t_start = (unsigned long)_text; 469 unsigned int level; 470 471 if (!kernel_set_to_readonly || !overlaps(start, end, t_start, t_end)) 472 return 0; 473 /* 474 * Don't enforce the !RW mapping for the kernel text mapping, if 475 * the current mapping is already using small page mapping. No 476 * need to work hard to preserve large page mappings in this case. 477 * 478 * This also fixes the Linux Xen paravirt guest boot failure caused 479 * by unexpected read-only mappings for kernel identity 480 * mappings. In this paravirt guest case, the kernel text mapping 481 * and the kernel identity mapping share the same page-table pages, 482 * so the protections for kernel text and identity mappings have to 483 * be the same. 484 */ 485 if (lookup_address(start, &level) && (level != PG_LEVEL_4K)) 486 return _PAGE_RW; 487 return 0; 488} 489#else 490static pgprotval_t protect_kernel_text_ro(unsigned long start, 491 unsigned long end) 492{ 493 return 0; 494} 495#endif 496 497static inline bool conflicts(pgprot_t prot, pgprotval_t val) 498{ 499 return (pgprot_val(prot) & ~val) != pgprot_val(prot); 500} 501 502static inline void check_conflict(int warnlvl, pgprot_t prot, pgprotval_t val, 503 unsigned long start, unsigned long end, 504 unsigned long pfn, const char *txt) 505{ 506 static const char *lvltxt[] = { 507 [CPA_CONFLICT] = "conflict", 508 [CPA_PROTECT] = "protect", 509 [CPA_DETECT] = "detect", 510 }; 511 512 if (warnlvl > cpa_warn_level || !conflicts(prot, val)) 513 return; 514 515 pr_warn("CPA %8s %10s: 0x%016lx - 0x%016lx PFN %lx req %016llx prevent %016llx\n", 516 lvltxt[warnlvl], txt, start, end, pfn, (unsigned long long)pgprot_val(prot), 517 (unsigned long long)val); 518} 519 520/* 521 * Certain areas of memory on x86 require very specific protection flags, 522 * for example the BIOS area or kernel text. Callers don't always get this 523 * right (again, ioremap() on BIOS memory is not uncommon) so this function 524 * checks and fixes these known static required protection bits. 525 */ 526static inline pgprot_t static_protections(pgprot_t prot, unsigned long start, 527 unsigned long pfn, unsigned long npg, 528 unsigned long lpsize, int warnlvl) 529{ 530 pgprotval_t forbidden, res; 531 unsigned long end; 532 533 /* 534 * There is no point in checking RW/NX conflicts when the requested 535 * mapping is setting the page !PRESENT. 536 */ 537 if (!(pgprot_val(prot) & _PAGE_PRESENT)) 538 return prot; 539 540 /* Operate on the virtual address */ 541 end = start + npg * PAGE_SIZE - 1; 542 543 res = protect_kernel_text(start, end); 544 check_conflict(warnlvl, prot, res, start, end, pfn, "Text NX"); 545 forbidden = res; 546 547 /* 548 * Special case to preserve a large page. If the change spawns the 549 * full large page mapping then there is no point to split it 550 * up. Happens with ftrace and is going to be removed once ftrace 551 * switched to text_poke(). 552 */ 553 if (lpsize != (npg * PAGE_SIZE) || (start & (lpsize - 1))) { 554 res = protect_kernel_text_ro(start, end); 555 check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO"); 556 forbidden |= res; 557 } 558 559 /* Check the PFN directly */ 560 res = protect_pci_bios(pfn, pfn + npg - 1); 561 check_conflict(warnlvl, prot, res, start, end, pfn, "PCIBIOS NX"); 562 forbidden |= res; 563 564 res = protect_rodata(pfn, pfn + npg - 1); 565 check_conflict(warnlvl, prot, res, start, end, pfn, "Rodata RO"); 566 forbidden |= res; 567 568 return __pgprot(pgprot_val(prot) & ~forbidden); 569} 570 571/* 572 * Lookup the page table entry for a virtual address in a specific pgd. 573 * Return a pointer to the entry and the level of the mapping. 574 */ 575pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, 576 unsigned int *level) 577{ 578 p4d_t *p4d; 579 pud_t *pud; 580 pmd_t *pmd; 581 582 *level = PG_LEVEL_NONE; 583 584 if (pgd_none(*pgd)) 585 return NULL; 586 587 p4d = p4d_offset(pgd, address); 588 if (p4d_none(*p4d)) 589 return NULL; 590 591 *level = PG_LEVEL_512G; 592 if (p4d_large(*p4d) || !p4d_present(*p4d)) 593 return (pte_t *)p4d; 594 595 pud = pud_offset(p4d, address); 596 if (pud_none(*pud)) 597 return NULL; 598 599 *level = PG_LEVEL_1G; 600 if (pud_large(*pud) || !pud_present(*pud)) 601 return (pte_t *)pud; 602 603 pmd = pmd_offset(pud, address); 604 if (pmd_none(*pmd)) 605 return NULL; 606 607 *level = PG_LEVEL_2M; 608 if (pmd_large(*pmd) || !pmd_present(*pmd)) 609 return (pte_t *)pmd; 610 611 *level = PG_LEVEL_4K; 612 613 return pte_offset_kernel(pmd, address); 614} 615 616/* 617 * Lookup the page table entry for a virtual address. Return a pointer 618 * to the entry and the level of the mapping. 619 * 620 * Note: We return pud and pmd either when the entry is marked large 621 * or when the present bit is not set. Otherwise we would return a 622 * pointer to a nonexisting mapping. 623 */ 624pte_t *lookup_address(unsigned long address, unsigned int *level) 625{ 626 return lookup_address_in_pgd(pgd_offset_k(address), address, level); 627} 628EXPORT_SYMBOL_GPL(lookup_address); 629 630/* 631 * Lookup the page table entry for a virtual address in a given mm. Return a 632 * pointer to the entry and the level of the mapping. 633 */ 634pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, 635 unsigned int *level) 636{ 637 return lookup_address_in_pgd(pgd_offset(mm, address), address, level); 638} 639EXPORT_SYMBOL_GPL(lookup_address_in_mm); 640 641static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, 642 unsigned int *level) 643{ 644 if (cpa->pgd) 645 return lookup_address_in_pgd(cpa->pgd + pgd_index(address), 646 address, level); 647 648 return lookup_address(address, level); 649} 650 651/* 652 * Lookup the PMD entry for a virtual address. Return a pointer to the entry 653 * or NULL if not present. 654 */ 655pmd_t *lookup_pmd_address(unsigned long address) 656{ 657 pgd_t *pgd; 658 p4d_t *p4d; 659 pud_t *pud; 660 661 pgd = pgd_offset_k(address); 662 if (pgd_none(*pgd)) 663 return NULL; 664 665 p4d = p4d_offset(pgd, address); 666 if (p4d_none(*p4d) || p4d_large(*p4d) || !p4d_present(*p4d)) 667 return NULL; 668 669 pud = pud_offset(p4d, address); 670 if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud)) 671 return NULL; 672 673 return pmd_offset(pud, address); 674} 675 676/* 677 * This is necessary because __pa() does not work on some 678 * kinds of memory, like vmalloc() or the alloc_remap() 679 * areas on 32-bit NUMA systems. The percpu areas can 680 * end up in this kind of memory, for instance. 681 * 682 * This could be optimized, but it is only intended to be 683 * used at inititalization time, and keeping it 684 * unoptimized should increase the testing coverage for 685 * the more obscure platforms. 686 */ 687phys_addr_t slow_virt_to_phys(void *__virt_addr) 688{ 689 unsigned long virt_addr = (unsigned long)__virt_addr; 690 phys_addr_t phys_addr; 691 unsigned long offset; 692 enum pg_level level; 693 pte_t *pte; 694 695 pte = lookup_address(virt_addr, &level); 696 BUG_ON(!pte); 697 698 /* 699 * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t 700 * before being left-shifted PAGE_SHIFT bits -- this trick is to 701 * make 32-PAE kernel work correctly. 702 */ 703 switch (level) { 704 case PG_LEVEL_1G: 705 phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; 706 offset = virt_addr & ~PUD_PAGE_MASK; 707 break; 708 case PG_LEVEL_2M: 709 phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; 710 offset = virt_addr & ~PMD_PAGE_MASK; 711 break; 712 default: 713 phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; 714 offset = virt_addr & ~PAGE_MASK; 715 } 716 717 return (phys_addr_t)(phys_addr | offset); 718} 719EXPORT_SYMBOL_GPL(slow_virt_to_phys); 720 721/* 722 * Set the new pmd in all the pgds we know about: 723 */ 724static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte) 725{ 726 /* change init_mm */ 727 set_pte_atomic(kpte, pte); 728#ifdef CONFIG_X86_32 729 if (!SHARED_KERNEL_PMD) { 730 struct page *page; 731 732 list_for_each_entry(page, &pgd_list, lru) { 733 pgd_t *pgd; 734 p4d_t *p4d; 735 pud_t *pud; 736 pmd_t *pmd; 737 738 pgd = (pgd_t *)page_address(page) + pgd_index(address); 739 p4d = p4d_offset(pgd, address); 740 pud = pud_offset(p4d, address); 741 pmd = pmd_offset(pud, address); 742 set_pte_atomic((pte_t *)pmd, pte); 743 } 744 } 745#endif 746} 747 748static pgprot_t pgprot_clear_protnone_bits(pgprot_t prot) 749{ 750 /* 751 * _PAGE_GLOBAL means "global page" for present PTEs. 752 * But, it is also used to indicate _PAGE_PROTNONE 753 * for non-present PTEs. 754 * 755 * This ensures that a _PAGE_GLOBAL PTE going from 756 * present to non-present is not confused as 757 * _PAGE_PROTNONE. 758 */ 759 if (!(pgprot_val(prot) & _PAGE_PRESENT)) 760 pgprot_val(prot) &= ~_PAGE_GLOBAL; 761 762 return prot; 763} 764 765static int __should_split_large_page(pte_t *kpte, unsigned long address, 766 struct cpa_data *cpa) 767{ 768 unsigned long numpages, pmask, psize, lpaddr, pfn, old_pfn; 769 pgprot_t old_prot, new_prot, req_prot, chk_prot; 770 pte_t new_pte, *tmp; 771 enum pg_level level; 772 773 /* 774 * Check for races, another CPU might have split this page 775 * up already: 776 */ 777 tmp = _lookup_address_cpa(cpa, address, &level); 778 if (tmp != kpte) 779 return 1; 780 781 switch (level) { 782 case PG_LEVEL_2M: 783 old_prot = pmd_pgprot(*(pmd_t *)kpte); 784 old_pfn = pmd_pfn(*(pmd_t *)kpte); 785 cpa_inc_2m_checked(); 786 break; 787 case PG_LEVEL_1G: 788 old_prot = pud_pgprot(*(pud_t *)kpte); 789 old_pfn = pud_pfn(*(pud_t *)kpte); 790 cpa_inc_1g_checked(); 791 break; 792 default: 793 return -EINVAL; 794 } 795 796 psize = page_level_size(level); 797 pmask = page_level_mask(level); 798 799 /* 800 * Calculate the number of pages, which fit into this large 801 * page starting at address: 802 */ 803 lpaddr = (address + psize) & pmask; 804 numpages = (lpaddr - address) >> PAGE_SHIFT; 805 if (numpages < cpa->numpages) 806 cpa->numpages = numpages; 807 808 /* 809 * We are safe now. Check whether the new pgprot is the same: 810 * Convert protection attributes to 4k-format, as cpa->mask* are set 811 * up accordingly. 812 */ 813 814 /* Clear PSE (aka _PAGE_PAT) and move PAT bit to correct position */ 815 req_prot = pgprot_large_2_4k(old_prot); 816 817 pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); 818 pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); 819 820 /* 821 * req_prot is in format of 4k pages. It must be converted to large 822 * page format: the caching mode includes the PAT bit located at 823 * different bit positions in the two formats. 824 */ 825 req_prot = pgprot_4k_2_large(req_prot); 826 req_prot = pgprot_clear_protnone_bits(req_prot); 827 if (pgprot_val(req_prot) & _PAGE_PRESENT) 828 pgprot_val(req_prot) |= _PAGE_PSE; 829 830 /* 831 * old_pfn points to the large page base pfn. So we need to add the 832 * offset of the virtual address: 833 */ 834 pfn = old_pfn + ((address & (psize - 1)) >> PAGE_SHIFT); 835 cpa->pfn = pfn; 836 837 /* 838 * Calculate the large page base address and the number of 4K pages 839 * in the large page 840 */ 841 lpaddr = address & pmask; 842 numpages = psize >> PAGE_SHIFT; 843 844 /* 845 * Sanity check that the existing mapping is correct versus the static 846 * protections. static_protections() guards against !PRESENT, so no 847 * extra conditional required here. 848 */ 849 chk_prot = static_protections(old_prot, lpaddr, old_pfn, numpages, 850 psize, CPA_CONFLICT); 851 852 if (WARN_ON_ONCE(pgprot_val(chk_prot) != pgprot_val(old_prot))) { 853 /* 854 * Split the large page and tell the split code to 855 * enforce static protections. 856 */ 857 cpa->force_static_prot = 1; 858 return 1; 859 } 860 861 /* 862 * Optimization: If the requested pgprot is the same as the current 863 * pgprot, then the large page can be preserved and no updates are 864 * required independent of alignment and length of the requested 865 * range. The above already established that the current pgprot is 866 * correct, which in consequence makes the requested pgprot correct 867 * as well if it is the same. The static protection scan below will 868 * not come to a different conclusion. 869 */ 870 if (pgprot_val(req_prot) == pgprot_val(old_prot)) { 871 cpa_inc_lp_sameprot(level); 872 return 0; 873 } 874 875 /* 876 * If the requested range does not cover the full page, split it up 877 */ 878 if (address != lpaddr || cpa->numpages != numpages) 879 return 1; 880 881 /* 882 * Check whether the requested pgprot is conflicting with a static 883 * protection requirement in the large page. 884 */ 885 new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages, 886 psize, CPA_DETECT); 887 888 /* 889 * If there is a conflict, split the large page. 890 * 891 * There used to be a 4k wise evaluation trying really hard to 892 * preserve the large pages, but experimentation has shown, that this 893 * does not help at all. There might be corner cases which would 894 * preserve one large page occasionally, but it's really not worth the 895 * extra code and cycles for the common case. 896 */ 897 if (pgprot_val(req_prot) != pgprot_val(new_prot)) 898 return 1; 899 900 /* All checks passed. Update the large page mapping. */ 901 new_pte = pfn_pte(old_pfn, new_prot); 902 __set_pmd_pte(kpte, address, new_pte); 903 cpa->flags |= CPA_FLUSHTLB; 904 cpa_inc_lp_preserved(level); 905 return 0; 906} 907 908static int should_split_large_page(pte_t *kpte, unsigned long address, 909 struct cpa_data *cpa) 910{ 911 int do_split; 912 913 if (cpa->force_split) 914 return 1; 915 916 spin_lock(&pgd_lock); 917 do_split = __should_split_large_page(kpte, address, cpa); 918 spin_unlock(&pgd_lock); 919 920 return do_split; 921} 922 923static void split_set_pte(struct cpa_data *cpa, pte_t *pte, unsigned long pfn, 924 pgprot_t ref_prot, unsigned long address, 925 unsigned long size) 926{ 927 unsigned int npg = PFN_DOWN(size); 928 pgprot_t prot; 929 930 /* 931 * If should_split_large_page() discovered an inconsistent mapping, 932 * remove the invalid protection in the split mapping. 933 */ 934 if (!cpa->force_static_prot) 935 goto set; 936 937 /* Hand in lpsize = 0 to enforce the protection mechanism */ 938 prot = static_protections(ref_prot, address, pfn, npg, 0, CPA_PROTECT); 939 940 if (pgprot_val(prot) == pgprot_val(ref_prot)) 941 goto set; 942 943 /* 944 * If this is splitting a PMD, fix it up. PUD splits cannot be 945 * fixed trivially as that would require to rescan the newly 946 * installed PMD mappings after returning from split_large_page() 947 * so an eventual further split can allocate the necessary PTE 948 * pages. Warn for now and revisit it in case this actually 949 * happens. 950 */ 951 if (size == PAGE_SIZE) 952 ref_prot = prot; 953 else 954 pr_warn_once("CPA: Cannot fixup static protections for PUD split\n"); 955set: 956 set_pte(pte, pfn_pte(pfn, ref_prot)); 957} 958 959static int 960__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, 961 struct page *base) 962{ 963 unsigned long lpaddr, lpinc, ref_pfn, pfn, pfninc = 1; 964 pte_t *pbase = (pte_t *)page_address(base); 965 unsigned int i, level; 966 pgprot_t ref_prot; 967 pte_t *tmp; 968 969 spin_lock(&pgd_lock); 970 /* 971 * Check for races, another CPU might have split this page 972 * up for us already: 973 */ 974 tmp = _lookup_address_cpa(cpa, address, &level); 975 if (tmp != kpte) { 976 spin_unlock(&pgd_lock); 977 return 1; 978 } 979 980 paravirt_alloc_pte(&init_mm, page_to_pfn(base)); 981 982 switch (level) { 983 case PG_LEVEL_2M: 984 ref_prot = pmd_pgprot(*(pmd_t *)kpte); 985 /* 986 * Clear PSE (aka _PAGE_PAT) and move 987 * PAT bit to correct position. 988 */ 989 ref_prot = pgprot_large_2_4k(ref_prot); 990 ref_pfn = pmd_pfn(*(pmd_t *)kpte); 991 lpaddr = address & PMD_MASK; 992 lpinc = PAGE_SIZE; 993 break; 994 995 case PG_LEVEL_1G: 996 ref_prot = pud_pgprot(*(pud_t *)kpte); 997 ref_pfn = pud_pfn(*(pud_t *)kpte); 998 pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; 999 lpaddr = address & PUD_MASK; 1000 lpinc = PMD_SIZE; 1001 /* 1002 * Clear the PSE flags if the PRESENT flag is not set 1003 * otherwise pmd_present/pmd_huge will return true 1004 * even on a non present pmd. 1005 */ 1006 if (!(pgprot_val(ref_prot) & _PAGE_PRESENT)) 1007 pgprot_val(ref_prot) &= ~_PAGE_PSE; 1008 break; 1009 1010 default: 1011 spin_unlock(&pgd_lock); 1012 return 1; 1013 } 1014 1015 ref_prot = pgprot_clear_protnone_bits(ref_prot); 1016 1017 /* 1018 * Get the target pfn from the original entry: 1019 */ 1020 pfn = ref_pfn; 1021 for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc, lpaddr += lpinc) 1022 split_set_pte(cpa, pbase + i, pfn, ref_prot, lpaddr, lpinc); 1023 1024 if (virt_addr_valid(address)) { 1025 unsigned long pfn = PFN_DOWN(__pa(address)); 1026 1027 if (pfn_range_is_mapped(pfn, pfn + 1)) 1028 split_page_count(level); 1029 } 1030 1031 /* 1032 * Install the new, split up pagetable. 1033 * 1034 * We use the standard kernel pagetable protections for the new 1035 * pagetable protections, the actual ptes set above control the 1036 * primary protection behavior: 1037 */ 1038 __set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE))); 1039 1040 /* 1041 * Do a global flush tlb after splitting the large page 1042 * and before we do the actual change page attribute in the PTE. 1043 * 1044 * Without this, we violate the TLB application note, that says: 1045 * "The TLBs may contain both ordinary and large-page 1046 * translations for a 4-KByte range of linear addresses. This 1047 * may occur if software modifies the paging structures so that 1048 * the page size used for the address range changes. If the two 1049 * translations differ with respect to page frame or attributes 1050 * (e.g., permissions), processor behavior is undefined and may 1051 * be implementation-specific." 1052 * 1053 * We do this global tlb flush inside the cpa_lock, so that we 1054 * don't allow any other cpu, with stale tlb entries change the 1055 * page attribute in parallel, that also falls into the 1056 * just split large page entry. 1057 */ 1058 flush_tlb_all(); 1059 spin_unlock(&pgd_lock); 1060 1061 return 0; 1062} 1063 1064static int split_large_page(struct cpa_data *cpa, pte_t *kpte, 1065 unsigned long address) 1066{ 1067 struct page *base; 1068 1069 if (!debug_pagealloc_enabled()) 1070 spin_unlock(&cpa_lock); 1071 base = alloc_pages(GFP_KERNEL, 0); 1072 if (!debug_pagealloc_enabled()) 1073 spin_lock(&cpa_lock); 1074 if (!base) 1075 return -ENOMEM; 1076 1077 if (__split_large_page(cpa, kpte, address, base)) 1078 __free_page(base); 1079 1080 return 0; 1081} 1082 1083static bool try_to_free_pte_page(pte_t *pte) 1084{ 1085 int i; 1086 1087 for (i = 0; i < PTRS_PER_PTE; i++) 1088 if (!pte_none(pte[i])) 1089 return false; 1090 1091 free_page((unsigned long)pte); 1092 return true; 1093} 1094 1095static bool try_to_free_pmd_page(pmd_t *pmd) 1096{ 1097 int i; 1098 1099 for (i = 0; i < PTRS_PER_PMD; i++) 1100 if (!pmd_none(pmd[i])) 1101 return false; 1102 1103 free_page((unsigned long)pmd); 1104 return true; 1105} 1106 1107static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end) 1108{ 1109 pte_t *pte = pte_offset_kernel(pmd, start); 1110 1111 while (start < end) { 1112 set_pte(pte, __pte(0)); 1113 1114 start += PAGE_SIZE; 1115 pte++; 1116 } 1117 1118 if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) { 1119 pmd_clear(pmd); 1120 return true; 1121 } 1122 return false; 1123} 1124 1125static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd, 1126 unsigned long start, unsigned long end) 1127{ 1128 if (unmap_pte_range(pmd, start, end)) 1129 if (try_to_free_pmd_page(pud_pgtable(*pud))) 1130 pud_clear(pud); 1131} 1132 1133static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) 1134{ 1135 pmd_t *pmd = pmd_offset(pud, start); 1136 1137 /* 1138 * Not on a 2MB page boundary? 1139 */ 1140 if (start & (PMD_SIZE - 1)) { 1141 unsigned long next_page = (start + PMD_SIZE) & PMD_MASK; 1142 unsigned long pre_end = min_t(unsigned long, end, next_page); 1143 1144 __unmap_pmd_range(pud, pmd, start, pre_end); 1145 1146 start = pre_end; 1147 pmd++; 1148 } 1149 1150 /* 1151 * Try to unmap in 2M chunks. 1152 */ 1153 while (end - start >= PMD_SIZE) { 1154 if (pmd_large(*pmd)) 1155 pmd_clear(pmd); 1156 else 1157 __unmap_pmd_range(pud, pmd, start, start + PMD_SIZE); 1158 1159 start += PMD_SIZE; 1160 pmd++; 1161 } 1162 1163 /* 1164 * 4K leftovers? 1165 */ 1166 if (start < end) 1167 return __unmap_pmd_range(pud, pmd, start, end); 1168 1169 /* 1170 * Try again to free the PMD page if haven't succeeded above. 1171 */ 1172 if (!pud_none(*pud)) 1173 if (try_to_free_pmd_page(pud_pgtable(*pud))) 1174 pud_clear(pud); 1175} 1176 1177static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end) 1178{ 1179 pud_t *pud = pud_offset(p4d, start); 1180 1181 /* 1182 * Not on a GB page boundary? 1183 */ 1184 if (start & (PUD_SIZE - 1)) { 1185 unsigned long next_page = (start + PUD_SIZE) & PUD_MASK; 1186 unsigned long pre_end = min_t(unsigned long, end, next_page); 1187 1188 unmap_pmd_range(pud, start, pre_end); 1189 1190 start = pre_end; 1191 pud++; 1192 } 1193 1194 /* 1195 * Try to unmap in 1G chunks? 1196 */ 1197 while (end - start >= PUD_SIZE) { 1198 1199 if (pud_large(*pud)) 1200 pud_clear(pud); 1201 else 1202 unmap_pmd_range(pud, start, start + PUD_SIZE); 1203 1204 start += PUD_SIZE; 1205 pud++; 1206 } 1207 1208 /* 1209 * 2M leftovers? 1210 */ 1211 if (start < end) 1212 unmap_pmd_range(pud, start, end); 1213 1214 /* 1215 * No need to try to free the PUD page because we'll free it in 1216 * populate_pgd's error path 1217 */ 1218} 1219 1220static int alloc_pte_page(pmd_t *pmd) 1221{ 1222 pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL); 1223 if (!pte) 1224 return -1; 1225 1226 set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE)); 1227 return 0; 1228} 1229 1230static int alloc_pmd_page(pud_t *pud) 1231{ 1232 pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL); 1233 if (!pmd) 1234 return -1; 1235 1236 set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); 1237 return 0; 1238} 1239 1240static void populate_pte(struct cpa_data *cpa, 1241 unsigned long start, unsigned long end, 1242 unsigned num_pages, pmd_t *pmd, pgprot_t pgprot) 1243{ 1244 pte_t *pte; 1245 1246 pte = pte_offset_kernel(pmd, start); 1247 1248 pgprot = pgprot_clear_protnone_bits(pgprot); 1249 1250 while (num_pages-- && start < end) { 1251 set_pte(pte, pfn_pte(cpa->pfn, pgprot)); 1252 1253 start += PAGE_SIZE; 1254 cpa->pfn++; 1255 pte++; 1256 } 1257} 1258 1259static long populate_pmd(struct cpa_data *cpa, 1260 unsigned long start, unsigned long end, 1261 unsigned num_pages, pud_t *pud, pgprot_t pgprot) 1262{ 1263 long cur_pages = 0; 1264 pmd_t *pmd; 1265 pgprot_t pmd_pgprot; 1266 1267 /* 1268 * Not on a 2M boundary? 1269 */ 1270 if (start & (PMD_SIZE - 1)) { 1271 unsigned long pre_end = start + (num_pages << PAGE_SHIFT); 1272 unsigned long next_page = (start + PMD_SIZE) & PMD_MASK; 1273 1274 pre_end = min_t(unsigned long, pre_end, next_page); 1275 cur_pages = (pre_end - start) >> PAGE_SHIFT; 1276 cur_pages = min_t(unsigned int, num_pages, cur_pages); 1277 1278 /* 1279 * Need a PTE page? 1280 */ 1281 pmd = pmd_offset(pud, start); 1282 if (pmd_none(*pmd)) 1283 if (alloc_pte_page(pmd)) 1284 return -1; 1285 1286 populate_pte(cpa, start, pre_end, cur_pages, pmd, pgprot); 1287 1288 start = pre_end; 1289 } 1290 1291 /* 1292 * We mapped them all? 1293 */ 1294 if (num_pages == cur_pages) 1295 return cur_pages; 1296 1297 pmd_pgprot = pgprot_4k_2_large(pgprot); 1298 1299 while (end - start >= PMD_SIZE) { 1300 1301 /* 1302 * We cannot use a 1G page so allocate a PMD page if needed. 1303 */ 1304 if (pud_none(*pud)) 1305 if (alloc_pmd_page(pud)) 1306 return -1; 1307 1308 pmd = pmd_offset(pud, start); 1309 1310 set_pmd(pmd, pmd_mkhuge(pfn_pmd(cpa->pfn, 1311 canon_pgprot(pmd_pgprot)))); 1312 1313 start += PMD_SIZE; 1314 cpa->pfn += PMD_SIZE >> PAGE_SHIFT; 1315 cur_pages += PMD_SIZE >> PAGE_SHIFT; 1316 } 1317 1318 /* 1319 * Map trailing 4K pages. 1320 */ 1321 if (start < end) { 1322 pmd = pmd_offset(pud, start); 1323 if (pmd_none(*pmd)) 1324 if (alloc_pte_page(pmd)) 1325 return -1; 1326 1327 populate_pte(cpa, start, end, num_pages - cur_pages, 1328 pmd, pgprot); 1329 } 1330 return num_pages; 1331} 1332 1333static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d, 1334 pgprot_t pgprot) 1335{ 1336 pud_t *pud; 1337 unsigned long end; 1338 long cur_pages = 0; 1339 pgprot_t pud_pgprot; 1340 1341 end = start + (cpa->numpages << PAGE_SHIFT); 1342 1343 /* 1344 * Not on a Gb page boundary? => map everything up to it with 1345 * smaller pages. 1346 */ 1347 if (start & (PUD_SIZE - 1)) { 1348 unsigned long pre_end; 1349 unsigned long next_page = (start + PUD_SIZE) & PUD_MASK; 1350 1351 pre_end = min_t(unsigned long, end, next_page); 1352 cur_pages = (pre_end - start) >> PAGE_SHIFT; 1353 cur_pages = min_t(int, (int)cpa->numpages, cur_pages); 1354 1355 pud = pud_offset(p4d, start); 1356 1357 /* 1358 * Need a PMD page? 1359 */ 1360 if (pud_none(*pud)) 1361 if (alloc_pmd_page(pud)) 1362 return -1; 1363 1364 cur_pages = populate_pmd(cpa, start, pre_end, cur_pages, 1365 pud, pgprot); 1366 if (cur_pages < 0) 1367 return cur_pages; 1368 1369 start = pre_end; 1370 } 1371 1372 /* We mapped them all? */ 1373 if (cpa->numpages == cur_pages) 1374 return cur_pages; 1375 1376 pud = pud_offset(p4d, start); 1377 pud_pgprot = pgprot_4k_2_large(pgprot); 1378 1379 /* 1380 * Map everything starting from the Gb boundary, possibly with 1G pages 1381 */ 1382 while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) { 1383 set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn, 1384 canon_pgprot(pud_pgprot)))); 1385 1386 start += PUD_SIZE; 1387 cpa->pfn += PUD_SIZE >> PAGE_SHIFT; 1388 cur_pages += PUD_SIZE >> PAGE_SHIFT; 1389 pud++; 1390 } 1391 1392 /* Map trailing leftover */ 1393 if (start < end) { 1394 long tmp; 1395 1396 pud = pud_offset(p4d, start); 1397 if (pud_none(*pud)) 1398 if (alloc_pmd_page(pud)) 1399 return -1; 1400 1401 tmp = populate_pmd(cpa, start, end, cpa->numpages - cur_pages, 1402 pud, pgprot); 1403 if (tmp < 0) 1404 return cur_pages; 1405 1406 cur_pages += tmp; 1407 } 1408 return cur_pages; 1409} 1410 1411/* 1412 * Restrictions for kernel page table do not necessarily apply when mapping in 1413 * an alternate PGD. 1414 */ 1415static int populate_pgd(struct cpa_data *cpa, unsigned long addr) 1416{ 1417 pgprot_t pgprot = __pgprot(_KERNPG_TABLE); 1418 pud_t *pud = NULL; /* shut up gcc */ 1419 p4d_t *p4d; 1420 pgd_t *pgd_entry; 1421 long ret; 1422 1423 pgd_entry = cpa->pgd + pgd_index(addr); 1424 1425 if (pgd_none(*pgd_entry)) { 1426 p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL); 1427 if (!p4d) 1428 return -1; 1429 1430 set_pgd(pgd_entry, __pgd(__pa(p4d) | _KERNPG_TABLE)); 1431 } 1432 1433 /* 1434 * Allocate a PUD page and hand it down for mapping. 1435 */ 1436 p4d = p4d_offset(pgd_entry, addr); 1437 if (p4d_none(*p4d)) { 1438 pud = (pud_t *)get_zeroed_page(GFP_KERNEL); 1439 if (!pud) 1440 return -1; 1441 1442 set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); 1443 } 1444 1445 pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr); 1446 pgprot_val(pgprot) |= pgprot_val(cpa->mask_set); 1447 1448 ret = populate_pud(cpa, addr, p4d, pgprot); 1449 if (ret < 0) { 1450 /* 1451 * Leave the PUD page in place in case some other CPU or thread 1452 * already found it, but remove any useless entries we just 1453 * added to it. 1454 */ 1455 unmap_pud_range(p4d, addr, 1456 addr + (cpa->numpages << PAGE_SHIFT)); 1457 return ret; 1458 } 1459 1460 cpa->numpages = ret; 1461 return 0; 1462} 1463 1464static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr, 1465 int primary) 1466{ 1467 if (cpa->pgd) { 1468 /* 1469 * Right now, we only execute this code path when mapping 1470 * the EFI virtual memory map regions, no other users 1471 * provide a ->pgd value. This may change in the future. 1472 */ 1473 return populate_pgd(cpa, vaddr); 1474 } 1475 1476 /* 1477 * Ignore all non primary paths. 1478 */ 1479 if (!primary) { 1480 cpa->numpages = 1; 1481 return 0; 1482 } 1483 1484 /* 1485 * Ignore the NULL PTE for kernel identity mapping, as it is expected 1486 * to have holes. 1487 * Also set numpages to '1' indicating that we processed cpa req for 1488 * one virtual address page and its pfn. TBD: numpages can be set based 1489 * on the initial value and the level returned by lookup_address(). 1490 */ 1491 if (within(vaddr, PAGE_OFFSET, 1492 PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) { 1493 cpa->numpages = 1; 1494 cpa->pfn = __pa(vaddr) >> PAGE_SHIFT; 1495 return 0; 1496 1497 } else if (__cpa_pfn_in_highmap(cpa->pfn)) { 1498 /* Faults in the highmap are OK, so do not warn: */ 1499 return -EFAULT; 1500 } else { 1501 WARN(1, KERN_WARNING "CPA: called for zero pte. " 1502 "vaddr = %lx cpa->vaddr = %lx\n", vaddr, 1503 *cpa->vaddr); 1504 1505 return -EFAULT; 1506 } 1507} 1508 1509static int __change_page_attr(struct cpa_data *cpa, int primary) 1510{ 1511 unsigned long address; 1512 int do_split, err; 1513 unsigned int level; 1514 pte_t *kpte, old_pte; 1515 1516 address = __cpa_addr(cpa, cpa->curpage); 1517repeat: 1518 kpte = _lookup_address_cpa(cpa, address, &level); 1519 if (!kpte) 1520 return __cpa_process_fault(cpa, address, primary); 1521 1522 old_pte = *kpte; 1523 if (pte_none(old_pte)) 1524 return __cpa_process_fault(cpa, address, primary); 1525 1526 if (level == PG_LEVEL_4K) { 1527 pte_t new_pte; 1528 pgprot_t new_prot = pte_pgprot(old_pte); 1529 unsigned long pfn = pte_pfn(old_pte); 1530 1531 pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr); 1532 pgprot_val(new_prot) |= pgprot_val(cpa->mask_set); 1533 1534 cpa_inc_4k_install(); 1535 /* Hand in lpsize = 0 to enforce the protection mechanism */ 1536 new_prot = static_protections(new_prot, address, pfn, 1, 0, 1537 CPA_PROTECT); 1538 1539 new_prot = pgprot_clear_protnone_bits(new_prot); 1540 1541 /* 1542 * We need to keep the pfn from the existing PTE, 1543 * after all we're only going to change it's attributes 1544 * not the memory it points to 1545 */ 1546 new_pte = pfn_pte(pfn, new_prot); 1547 cpa->pfn = pfn; 1548 /* 1549 * Do we really change anything ? 1550 */ 1551 if (pte_val(old_pte) != pte_val(new_pte)) { 1552 set_pte_atomic(kpte, new_pte); 1553 cpa->flags |= CPA_FLUSHTLB; 1554 } 1555 cpa->numpages = 1; 1556 return 0; 1557 } 1558 1559 /* 1560 * Check, whether we can keep the large page intact 1561 * and just change the pte: 1562 */ 1563 do_split = should_split_large_page(kpte, address, cpa); 1564 /* 1565 * When the range fits into the existing large page, 1566 * return. cp->numpages and cpa->tlbflush have been updated in 1567 * try_large_page: 1568 */ 1569 if (do_split <= 0) 1570 return do_split; 1571 1572 /* 1573 * We have to split the large page: 1574 */ 1575 err = split_large_page(cpa, kpte, address); 1576 if (!err) 1577 goto repeat; 1578 1579 return err; 1580} 1581 1582static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias); 1583 1584static int cpa_process_alias(struct cpa_data *cpa) 1585{ 1586 struct cpa_data alias_cpa; 1587 unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT); 1588 unsigned long vaddr; 1589 int ret; 1590 1591 if (!pfn_range_is_mapped(cpa->pfn, cpa->pfn + 1)) 1592 return 0; 1593 1594 /* 1595 * No need to redo, when the primary call touched the direct 1596 * mapping already: 1597 */ 1598 vaddr = __cpa_addr(cpa, cpa->curpage); 1599 if (!(within(vaddr, PAGE_OFFSET, 1600 PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) { 1601 1602 alias_cpa = *cpa; 1603 alias_cpa.vaddr = &laddr; 1604 alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); 1605 alias_cpa.curpage = 0; 1606 1607 cpa->force_flush_all = 1; 1608 1609 ret = __change_page_attr_set_clr(&alias_cpa, 0); 1610 if (ret) 1611 return ret; 1612 } 1613 1614#ifdef CONFIG_X86_64 1615 /* 1616 * If the primary call didn't touch the high mapping already 1617 * and the physical address is inside the kernel map, we need 1618 * to touch the high mapped kernel as well: 1619 */ 1620 if (!within(vaddr, (unsigned long)_text, _brk_end) && 1621 __cpa_pfn_in_highmap(cpa->pfn)) { 1622 unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + 1623 __START_KERNEL_map - phys_base; 1624 alias_cpa = *cpa; 1625 alias_cpa.vaddr = &temp_cpa_vaddr; 1626 alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); 1627 alias_cpa.curpage = 0; 1628 1629 cpa->force_flush_all = 1; 1630 /* 1631 * The high mapping range is imprecise, so ignore the 1632 * return value. 1633 */ 1634 __change_page_attr_set_clr(&alias_cpa, 0); 1635 } 1636#endif 1637 1638 return 0; 1639} 1640 1641static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) 1642{ 1643 unsigned long numpages = cpa->numpages; 1644 unsigned long rempages = numpages; 1645 int ret = 0; 1646 1647 while (rempages) { 1648 /* 1649 * Store the remaining nr of pages for the large page 1650 * preservation check. 1651 */ 1652 cpa->numpages = rempages; 1653 /* for array changes, we can't use large page */ 1654 if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY)) 1655 cpa->numpages = 1; 1656 1657 if (!debug_pagealloc_enabled()) 1658 spin_lock(&cpa_lock); 1659 ret = __change_page_attr(cpa, checkalias); 1660 if (!debug_pagealloc_enabled()) 1661 spin_unlock(&cpa_lock); 1662 if (ret) 1663 goto out; 1664 1665 if (checkalias) { 1666 ret = cpa_process_alias(cpa); 1667 if (ret) 1668 goto out; 1669 } 1670 1671 /* 1672 * Adjust the number of pages with the result of the 1673 * CPA operation. Either a large page has been 1674 * preserved or a single page update happened. 1675 */ 1676 BUG_ON(cpa->numpages > rempages || !cpa->numpages); 1677 rempages -= cpa->numpages; 1678 cpa->curpage += cpa->numpages; 1679 } 1680 1681out: 1682 /* Restore the original numpages */ 1683 cpa->numpages = numpages; 1684 return ret; 1685} 1686 1687static int change_page_attr_set_clr(unsigned long *addr, int numpages, 1688 pgprot_t mask_set, pgprot_t mask_clr, 1689 int force_split, int in_flag, 1690 struct page **pages) 1691{ 1692 struct cpa_data cpa; 1693 int ret, cache, checkalias; 1694 1695 memset(&cpa, 0, sizeof(cpa)); 1696 1697 /* 1698 * Check, if we are requested to set a not supported 1699 * feature. Clearing non-supported features is OK. 1700 */ 1701 mask_set = canon_pgprot(mask_set); 1702 1703 if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split) 1704 return 0; 1705 1706 /* Ensure we are PAGE_SIZE aligned */ 1707 if (in_flag & CPA_ARRAY) { 1708 int i; 1709 for (i = 0; i < numpages; i++) { 1710 if (addr[i] & ~PAGE_MASK) { 1711 addr[i] &= PAGE_MASK; 1712 WARN_ON_ONCE(1); 1713 } 1714 } 1715 } else if (!(in_flag & CPA_PAGES_ARRAY)) { 1716 /* 1717 * in_flag of CPA_PAGES_ARRAY implies it is aligned. 1718 * No need to check in that case 1719 */ 1720 if (*addr & ~PAGE_MASK) { 1721 *addr &= PAGE_MASK; 1722 /* 1723 * People should not be passing in unaligned addresses: 1724 */ 1725 WARN_ON_ONCE(1); 1726 } 1727 } 1728 1729 /* Must avoid aliasing mappings in the highmem code */ 1730 kmap_flush_unused(); 1731 1732 vm_unmap_aliases(); 1733 1734 cpa.vaddr = addr; 1735 cpa.pages = pages; 1736 cpa.numpages = numpages; 1737 cpa.mask_set = mask_set; 1738 cpa.mask_clr = mask_clr; 1739 cpa.flags = 0; 1740 cpa.curpage = 0; 1741 cpa.force_split = force_split; 1742 1743 if (in_flag & (CPA_ARRAY | CPA_PAGES_ARRAY)) 1744 cpa.flags |= in_flag; 1745 1746 /* No alias checking for _NX bit modifications */ 1747 checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX; 1748 /* Has caller explicitly disabled alias checking? */ 1749 if (in_flag & CPA_NO_CHECK_ALIAS) 1750 checkalias = 0; 1751 1752 ret = __change_page_attr_set_clr(&cpa, checkalias); 1753 1754 /* 1755 * Check whether we really changed something: 1756 */ 1757 if (!(cpa.flags & CPA_FLUSHTLB)) 1758 goto out; 1759 1760 /* 1761 * No need to flush, when we did not set any of the caching 1762 * attributes: 1763 */ 1764 cache = !!pgprot2cachemode(mask_set); 1765 1766 /* 1767 * On error; flush everything to be sure. 1768 */ 1769 if (ret) { 1770 cpa_flush_all(cache); 1771 goto out; 1772 } 1773 1774 cpa_flush(&cpa, cache); 1775out: 1776 return ret; 1777} 1778 1779static inline int change_page_attr_set(unsigned long *addr, int numpages, 1780 pgprot_t mask, int array) 1781{ 1782 return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0, 1783 (array ? CPA_ARRAY : 0), NULL); 1784} 1785 1786static inline int change_page_attr_clear(unsigned long *addr, int numpages, 1787 pgprot_t mask, int array) 1788{ 1789 return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0, 1790 (array ? CPA_ARRAY : 0), NULL); 1791} 1792 1793static inline int cpa_set_pages_array(struct page **pages, int numpages, 1794 pgprot_t mask) 1795{ 1796 return change_page_attr_set_clr(NULL, numpages, mask, __pgprot(0), 0, 1797 CPA_PAGES_ARRAY, pages); 1798} 1799 1800static inline int cpa_clear_pages_array(struct page **pages, int numpages, 1801 pgprot_t mask) 1802{ 1803 return change_page_attr_set_clr(NULL, numpages, __pgprot(0), mask, 0, 1804 CPA_PAGES_ARRAY, pages); 1805} 1806 1807/* 1808 * _set_memory_prot is an internal helper for callers that have been passed 1809 * a pgprot_t value from upper layers and a reservation has already been taken. 1810 * If you want to set the pgprot to a specific page protocol, use the 1811 * set_memory_xx() functions. 1812 */ 1813int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot) 1814{ 1815 return change_page_attr_set_clr(&addr, numpages, prot, 1816 __pgprot(~pgprot_val(prot)), 0, 0, 1817 NULL); 1818} 1819 1820int _set_memory_uc(unsigned long addr, int numpages) 1821{ 1822 /* 1823 * for now UC MINUS. see comments in ioremap() 1824 * If you really need strong UC use ioremap_uc(), but note 1825 * that you cannot override IO areas with set_memory_*() as 1826 * these helpers cannot work with IO memory. 1827 */ 1828 return change_page_attr_set(&addr, numpages, 1829 cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), 1830 0); 1831} 1832 1833int set_memory_uc(unsigned long addr, int numpages) 1834{ 1835 int ret; 1836 1837 /* 1838 * for now UC MINUS. see comments in ioremap() 1839 */ 1840 ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, 1841 _PAGE_CACHE_MODE_UC_MINUS, NULL); 1842 if (ret) 1843 goto out_err; 1844 1845 ret = _set_memory_uc(addr, numpages); 1846 if (ret) 1847 goto out_free; 1848 1849 return 0; 1850 1851out_free: 1852 memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); 1853out_err: 1854 return ret; 1855} 1856EXPORT_SYMBOL(set_memory_uc); 1857 1858int _set_memory_wc(unsigned long addr, int numpages) 1859{ 1860 int ret; 1861 1862 ret = change_page_attr_set(&addr, numpages, 1863 cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), 1864 0); 1865 if (!ret) { 1866 ret = change_page_attr_set_clr(&addr, numpages, 1867 cachemode2pgprot(_PAGE_CACHE_MODE_WC), 1868 __pgprot(_PAGE_CACHE_MASK), 1869 0, 0, NULL); 1870 } 1871 return ret; 1872} 1873 1874int set_memory_wc(unsigned long addr, int numpages) 1875{ 1876 int ret; 1877 1878 ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, 1879 _PAGE_CACHE_MODE_WC, NULL); 1880 if (ret) 1881 return ret; 1882 1883 ret = _set_memory_wc(addr, numpages); 1884 if (ret) 1885 memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); 1886 1887 return ret; 1888} 1889EXPORT_SYMBOL(set_memory_wc); 1890 1891int _set_memory_wt(unsigned long addr, int numpages) 1892{ 1893 return change_page_attr_set(&addr, numpages, 1894 cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0); 1895} 1896 1897int _set_memory_wb(unsigned long addr, int numpages) 1898{ 1899 /* WB cache mode is hard wired to all cache attribute bits being 0 */ 1900 return change_page_attr_clear(&addr, numpages, 1901 __pgprot(_PAGE_CACHE_MASK), 0); 1902} 1903 1904int set_memory_wb(unsigned long addr, int numpages) 1905{ 1906 int ret; 1907 1908 ret = _set_memory_wb(addr, numpages); 1909 if (ret) 1910 return ret; 1911 1912 memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); 1913 return 0; 1914} 1915EXPORT_SYMBOL(set_memory_wb); 1916 1917int set_memory_x(unsigned long addr, int numpages) 1918{ 1919 if (!(__supported_pte_mask & _PAGE_NX)) 1920 return 0; 1921 1922 return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_NX), 0); 1923} 1924 1925int set_memory_nx(unsigned long addr, int numpages) 1926{ 1927 if (!(__supported_pte_mask & _PAGE_NX)) 1928 return 0; 1929 1930 return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_NX), 0); 1931} 1932 1933int set_memory_ro(unsigned long addr, int numpages) 1934{ 1935 return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_RW), 0); 1936} 1937 1938int set_memory_rw(unsigned long addr, int numpages) 1939{ 1940 return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_RW), 0); 1941} 1942 1943int set_memory_np(unsigned long addr, int numpages) 1944{ 1945 return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); 1946} 1947 1948int set_memory_np_noalias(unsigned long addr, int numpages) 1949{ 1950 int cpa_flags = CPA_NO_CHECK_ALIAS; 1951 1952 return change_page_attr_set_clr(&addr, numpages, __pgprot(0), 1953 __pgprot(_PAGE_PRESENT), 0, 1954 cpa_flags, NULL); 1955} 1956 1957int set_memory_4k(unsigned long addr, int numpages) 1958{ 1959 return change_page_attr_set_clr(&addr, numpages, __pgprot(0), 1960 __pgprot(0), 1, 0, NULL); 1961} 1962 1963int set_memory_nonglobal(unsigned long addr, int numpages) 1964{ 1965 return change_page_attr_clear(&addr, numpages, 1966 __pgprot(_PAGE_GLOBAL), 0); 1967} 1968 1969int set_memory_global(unsigned long addr, int numpages) 1970{ 1971 return change_page_attr_set(&addr, numpages, 1972 __pgprot(_PAGE_GLOBAL), 0); 1973} 1974 1975static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) 1976{ 1977 struct cpa_data cpa; 1978 int ret; 1979 1980 /* Nothing to do if memory encryption is not active */ 1981 if (!mem_encrypt_active()) 1982 return 0; 1983 1984 /* Should not be working on unaligned addresses */ 1985 if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr)) 1986 addr &= PAGE_MASK; 1987 1988 memset(&cpa, 0, sizeof(cpa)); 1989 cpa.vaddr = &addr; 1990 cpa.numpages = numpages; 1991 cpa.mask_set = enc ? __pgprot(_PAGE_ENC) : __pgprot(0); 1992 cpa.mask_clr = enc ? __pgprot(0) : __pgprot(_PAGE_ENC); 1993 cpa.pgd = init_mm.pgd; 1994 1995 /* Must avoid aliasing mappings in the highmem code */ 1996 kmap_flush_unused(); 1997 vm_unmap_aliases(); 1998 1999 /* 2000 * Before changing the encryption attribute, we need to flush caches. 2001 */ 2002 cpa_flush(&cpa, !this_cpu_has(X86_FEATURE_SME_COHERENT)); 2003 2004 ret = __change_page_attr_set_clr(&cpa, 1); 2005 2006 /* 2007 * After changing the encryption attribute, we need to flush TLBs again 2008 * in case any speculative TLB caching occurred (but no need to flush 2009 * caches again). We could just use cpa_flush_all(), but in case TLB 2010 * flushing gets optimized in the cpa_flush() path use the same logic 2011 * as above. 2012 */ 2013 cpa_flush(&cpa, 0); 2014 2015 return ret; 2016} 2017 2018int set_memory_encrypted(unsigned long addr, int numpages) 2019{ 2020 return __set_memory_enc_dec(addr, numpages, true); 2021} 2022EXPORT_SYMBOL_GPL(set_memory_encrypted); 2023 2024int set_memory_decrypted(unsigned long addr, int numpages) 2025{ 2026 return __set_memory_enc_dec(addr, numpages, false); 2027} 2028EXPORT_SYMBOL_GPL(set_memory_decrypted); 2029 2030int set_pages_uc(struct page *page, int numpages) 2031{ 2032 unsigned long addr = (unsigned long)page_address(page); 2033 2034 return set_memory_uc(addr, numpages); 2035} 2036EXPORT_SYMBOL(set_pages_uc); 2037 2038static int _set_pages_array(struct page **pages, int numpages, 2039 enum page_cache_mode new_type) 2040{ 2041 unsigned long start; 2042 unsigned long end; 2043 enum page_cache_mode set_type; 2044 int i; 2045 int free_idx; 2046 int ret; 2047 2048 for (i = 0; i < numpages; i++) { 2049 if (PageHighMem(pages[i])) 2050 continue; 2051 start = page_to_pfn(pages[i]) << PAGE_SHIFT; 2052 end = start + PAGE_SIZE; 2053 if (memtype_reserve(start, end, new_type, NULL)) 2054 goto err_out; 2055 } 2056 2057 /* If WC, set to UC- first and then WC */ 2058 set_type = (new_type == _PAGE_CACHE_MODE_WC) ? 2059 _PAGE_CACHE_MODE_UC_MINUS : new_type; 2060 2061 ret = cpa_set_pages_array(pages, numpages, 2062 cachemode2pgprot(set_type)); 2063 if (!ret && new_type == _PAGE_CACHE_MODE_WC) 2064 ret = change_page_attr_set_clr(NULL, numpages, 2065 cachemode2pgprot( 2066 _PAGE_CACHE_MODE_WC), 2067 __pgprot(_PAGE_CACHE_MASK), 2068 0, CPA_PAGES_ARRAY, pages); 2069 if (ret) 2070 goto err_out; 2071 return 0; /* Success */ 2072err_out: 2073 free_idx = i; 2074 for (i = 0; i < free_idx; i++) { 2075 if (PageHighMem(pages[i])) 2076 continue; 2077 start = page_to_pfn(pages[i]) << PAGE_SHIFT; 2078 end = start + PAGE_SIZE; 2079 memtype_free(start, end); 2080 } 2081 return -EINVAL; 2082} 2083 2084int set_pages_array_uc(struct page **pages, int numpages) 2085{ 2086 return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_UC_MINUS); 2087} 2088EXPORT_SYMBOL(set_pages_array_uc); 2089 2090int set_pages_array_wc(struct page **pages, int numpages) 2091{ 2092 return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_WC); 2093} 2094EXPORT_SYMBOL(set_pages_array_wc); 2095 2096int set_pages_array_wt(struct page **pages, int numpages) 2097{ 2098 return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_WT); 2099} 2100EXPORT_SYMBOL_GPL(set_pages_array_wt); 2101 2102int set_pages_wb(struct page *page, int numpages) 2103{ 2104 unsigned long addr = (unsigned long)page_address(page); 2105 2106 return set_memory_wb(addr, numpages); 2107} 2108EXPORT_SYMBOL(set_pages_wb); 2109 2110int set_pages_array_wb(struct page **pages, int numpages) 2111{ 2112 int retval; 2113 unsigned long start; 2114 unsigned long end; 2115 int i; 2116 2117 /* WB cache mode is hard wired to all cache attribute bits being 0 */ 2118 retval = cpa_clear_pages_array(pages, numpages, 2119 __pgprot(_PAGE_CACHE_MASK)); 2120 if (retval) 2121 return retval; 2122 2123 for (i = 0; i < numpages; i++) { 2124 if (PageHighMem(pages[i])) 2125 continue; 2126 start = page_to_pfn(pages[i]) << PAGE_SHIFT; 2127 end = start + PAGE_SIZE; 2128 memtype_free(start, end); 2129 } 2130 2131 return 0; 2132} 2133EXPORT_SYMBOL(set_pages_array_wb); 2134 2135int set_pages_ro(struct page *page, int numpages) 2136{ 2137 unsigned long addr = (unsigned long)page_address(page); 2138 2139 return set_memory_ro(addr, numpages); 2140} 2141 2142int set_pages_rw(struct page *page, int numpages) 2143{ 2144 unsigned long addr = (unsigned long)page_address(page); 2145 2146 return set_memory_rw(addr, numpages); 2147} 2148 2149static int __set_pages_p(struct page *page, int numpages) 2150{ 2151 unsigned long tempaddr = (unsigned long) page_address(page); 2152 struct cpa_data cpa = { .vaddr = &tempaddr, 2153 .pgd = NULL, 2154 .numpages = numpages, 2155 .mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW), 2156 .mask_clr = __pgprot(0), 2157 .flags = 0}; 2158 2159 /* 2160 * No alias checking needed for setting present flag. otherwise, 2161 * we may need to break large pages for 64-bit kernel text 2162 * mappings (this adds to complexity if we want to do this from 2163 * atomic context especially). Let's keep it simple! 2164 */ 2165 return __change_page_attr_set_clr(&cpa, 0); 2166} 2167 2168static int __set_pages_np(struct page *page, int numpages) 2169{ 2170 unsigned long tempaddr = (unsigned long) page_address(page); 2171 struct cpa_data cpa = { .vaddr = &tempaddr, 2172 .pgd = NULL, 2173 .numpages = numpages, 2174 .mask_set = __pgprot(0), 2175 .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW), 2176 .flags = 0}; 2177 2178 /* 2179 * No alias checking needed for setting not present flag. otherwise, 2180 * we may need to break large pages for 64-bit kernel text 2181 * mappings (this adds to complexity if we want to do this from 2182 * atomic context especially). Let's keep it simple! 2183 */ 2184 return __change_page_attr_set_clr(&cpa, 0); 2185} 2186 2187int set_direct_map_invalid_noflush(struct page *page) 2188{ 2189 return __set_pages_np(page, 1); 2190} 2191 2192int set_direct_map_default_noflush(struct page *page) 2193{ 2194 return __set_pages_p(page, 1); 2195} 2196 2197void __kernel_map_pages(struct page *page, int numpages, int enable) 2198{ 2199 if (PageHighMem(page)) 2200 return; 2201 if (!enable) { 2202 debug_check_no_locks_freed(page_address(page), 2203 numpages * PAGE_SIZE); 2204 } 2205 2206 /* 2207 * The return value is ignored as the calls cannot fail. 2208 * Large pages for identity mappings are not used at boot time 2209 * and hence no memory allocations during large page split. 2210 */ 2211 if (enable) 2212 __set_pages_p(page, numpages); 2213 else 2214 __set_pages_np(page, numpages); 2215 2216 /* 2217 * We should perform an IPI and flush all tlbs, 2218 * but that can deadlock->flush only current cpu. 2219 * Preemption needs to be disabled around __flush_tlb_all() due to 2220 * CR3 reload in __native_flush_tlb(). 2221 */ 2222 preempt_disable(); 2223 __flush_tlb_all(); 2224 preempt_enable(); 2225 2226 arch_flush_lazy_mmu_mode(); 2227} 2228 2229#ifdef CONFIG_HIBERNATION 2230bool kernel_page_present(struct page *page) 2231{ 2232 unsigned int level; 2233 pte_t *pte; 2234 2235 if (PageHighMem(page)) 2236 return false; 2237 2238 pte = lookup_address((unsigned long)page_address(page), &level); 2239 return (pte_val(*pte) & _PAGE_PRESENT); 2240} 2241#endif /* CONFIG_HIBERNATION */ 2242 2243int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, 2244 unsigned numpages, unsigned long page_flags) 2245{ 2246 int retval = -EINVAL; 2247 2248 struct cpa_data cpa = { 2249 .vaddr = &address, 2250 .pfn = pfn, 2251 .pgd = pgd, 2252 .numpages = numpages, 2253 .mask_set = __pgprot(0), 2254 .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)), 2255 .flags = 0, 2256 }; 2257 2258 WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP"); 2259 2260 if (!(__supported_pte_mask & _PAGE_NX)) 2261 goto out; 2262 2263 if (!(page_flags & _PAGE_ENC)) 2264 cpa.mask_clr = pgprot_encrypted(cpa.mask_clr); 2265 2266 cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags); 2267 2268 retval = __change_page_attr_set_clr(&cpa, 0); 2269 __flush_tlb_all(); 2270 2271out: 2272 return retval; 2273} 2274 2275/* 2276 * __flush_tlb_all() flushes mappings only on current CPU and hence this 2277 * function shouldn't be used in an SMP environment. Presently, it's used only 2278 * during boot (way before smp_init()) by EFI subsystem and hence is ok. 2279 */ 2280int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, 2281 unsigned long numpages) 2282{ 2283 int retval; 2284 2285 /* 2286 * The typical sequence for unmapping is to find a pte through 2287 * lookup_address_in_pgd() (ideally, it should never return NULL because 2288 * the address is already mapped) and change it's protections. As pfn is 2289 * the *target* of a mapping, it's not useful while unmapping. 2290 */ 2291 struct cpa_data cpa = { 2292 .vaddr = &address, 2293 .pfn = 0, 2294 .pgd = pgd, 2295 .numpages = numpages, 2296 .mask_set = __pgprot(0), 2297 .mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW), 2298 .flags = 0, 2299 }; 2300 2301 WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP"); 2302 2303 retval = __change_page_attr_set_clr(&cpa, 0); 2304 __flush_tlb_all(); 2305 2306 return retval; 2307} 2308 2309/* 2310 * The testcases use internal knowledge of the implementation that shouldn't 2311 * be exposed to the rest of the kernel. Include these directly here. 2312 */ 2313#ifdef CONFIG_CPA_DEBUG 2314#include "cpa-test.c" 2315#endif 2316