/* * Based on arch/arm/mm/mmu.c * * Copyright (C) 1995-2005 Russell King * Copyright (C) 2012 ARM Ltd. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program. If not, see . */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include u64 idmap_t0sz = TCR_T0SZ(VA_BITS); u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); /* * Empty_zero_page is a special page that is used for zero-initialized data * and COW. */ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss; static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused; static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused; pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { if (!pfn_valid(pfn)) return pgprot_noncached(vma_prot); else if (file->f_flags & O_SYNC) return pgprot_writecombine(vma_prot); return vma_prot; } EXPORT_SYMBOL(phys_mem_access_prot); static phys_addr_t __init early_pgtable_alloc(void) { phys_addr_t phys; void *ptr; phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE); /* * The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE * slot will be free, so we can (ab)use the FIX_PTE slot to initialise * any level of table. */ ptr = pte_set_fixmap(phys); memset(ptr, 0, PAGE_SIZE); /* * Implicit barriers also ensure the zeroed page is visible to the page * table walker */ pte_clear_fixmap(); return phys; } static bool pgattr_change_is_safe(u64 old, u64 new) { /* * The following mapping attributes may be updated in live * kernel mappings without the need for break-before-make. */ static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE; return old == 0 || new == 0 || ((old ^ new) & ~mask) == 0; } static void alloc_init_pte(pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), bool page_mappings_only) { pgprot_t __prot = prot; pte_t *pte; BUG_ON(pmd_sect(*pmd)); if (pmd_none(*pmd)) { phys_addr_t pte_phys; BUG_ON(!pgtable_alloc); pte_phys = pgtable_alloc(); pte = pte_set_fixmap(pte_phys); __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); pte_clear_fixmap(); } BUG_ON(pmd_bad(*pmd)); pte = pte_set_fixmap_offset(pmd, addr); do { pte_t old_pte = *pte; /* * Set the contiguous bit for the subsequent group of PTEs if * its size and alignment are appropriate. */ if (((addr | PFN_PHYS(pfn)) & ~CONT_PTE_MASK) == 0) { if (end - addr >= CONT_PTE_SIZE && !page_mappings_only) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); else __prot = prot; } set_pte(pte, pfn_pte(pfn, __prot)); pfn++; /* * After the PTE entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(*pte))); } while (pte++, addr += PAGE_SIZE, addr != end); pte_clear_fixmap(); } static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), bool page_mappings_only) { pgprot_t __prot = prot; pmd_t *pmd; unsigned long next; /* * Check for initial section mappings in the pgd/pud and remove them. */ BUG_ON(pud_sect(*pud)); if (pud_none(*pud)) { phys_addr_t pmd_phys; BUG_ON(!pgtable_alloc); pmd_phys = pgtable_alloc(); pmd = pmd_set_fixmap(pmd_phys); __pud_populate(pud, pmd_phys, PUD_TYPE_TABLE); pmd_clear_fixmap(); } BUG_ON(pud_bad(*pud)); pmd = pmd_set_fixmap_offset(pud, addr); do { pmd_t old_pmd = *pmd; next = pmd_addr_end(addr, end); /* try section mapping first */ if (((addr | next | phys) & ~SECTION_MASK) == 0 && !page_mappings_only) { /* * Set the contiguous bit for the subsequent group of * PMDs if its size and alignment are appropriate. */ if (((addr | phys) & ~CONT_PMD_MASK) == 0) { if (end - addr >= CONT_PMD_SIZE) __prot = __pgprot(pgprot_val(prot) | PTE_CONT); else __prot = prot; } pmd_set_huge(pmd, phys, __prot); /* * After the PMD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd), pmd_val(*pmd))); } else { alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys), prot, pgtable_alloc, page_mappings_only); BUG_ON(pmd_val(old_pmd) != 0 && pmd_val(old_pmd) != pmd_val(*pmd)); } phys += next - addr; } while (pmd++, addr = next, addr != end); pmd_clear_fixmap(); } static inline bool use_1G_block(unsigned long addr, unsigned long next, unsigned long phys) { if (PAGE_SHIFT != 12) return false; if (((addr | next | phys) & ~PUD_MASK) != 0) return false; return true; } static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), bool page_mappings_only) { pud_t *pud; unsigned long next; if (pgd_none(*pgd)) { phys_addr_t pud_phys; BUG_ON(!pgtable_alloc); pud_phys = pgtable_alloc(); __pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE); } BUG_ON(pgd_bad(*pgd)); pud = pud_set_fixmap_offset(pgd, addr); do { pud_t old_pud = *pud; next = pud_addr_end(addr, end); /* * For 4K granule only, attempt to put down a 1GB block */ if (use_1G_block(addr, next, phys) && !page_mappings_only) { pud_set_huge(pud, phys, prot); /* * After the PUD entry has been populated once, we * only allow updates to the permission attributes. */ BUG_ON(!pgattr_change_is_safe(pud_val(old_pud), pud_val(*pud))); } else { alloc_init_pmd(pud, addr, next, phys, prot, pgtable_alloc, page_mappings_only); BUG_ON(pud_val(old_pud) != 0 && pud_val(old_pud) != pud_val(*pud)); } phys += next - addr; } while (pud++, addr = next, addr != end); pud_clear_fixmap(); } static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, phys_addr_t (*pgtable_alloc)(void), bool page_mappings_only) { unsigned long addr, length, end, next; pgd_t *pgd = pgd_offset_raw(pgdir, virt); /* * If the virtual and physical address don't have the same offset * within a page, we cannot map the region as the caller expects. */ if (WARN_ON((phys ^ virt) & ~PAGE_MASK)) return; phys &= PAGE_MASK; addr = virt & PAGE_MASK; length = PAGE_ALIGN(size + (virt & ~PAGE_MASK)); end = addr + length; do { next = pgd_addr_end(addr, end); alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc, page_mappings_only); phys += next - addr; } while (pgd++, addr = next, addr != end); } static phys_addr_t pgd_pgtable_alloc(void) { void *ptr = (void *)__get_free_page(PGALLOC_GFP); if (!ptr || !pgtable_page_ctor(virt_to_page(ptr))) BUG(); /* Ensure the zeroed page is visible to the page table walker */ dsb(ishst); return __pa(ptr); } /* * This function can only be used to modify existing table entries, * without allocating new levels of table. Note that this permits the * creation of new section or page entries. */ static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { if (virt < VMALLOC_START) { pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; } __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, false); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, bool page_mappings_only) { BUG_ON(mm == &init_mm); __create_pgd_mapping(mm->pgd, phys, virt, size, prot, pgd_pgtable_alloc, page_mappings_only); } static void create_mapping_late(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { if (virt < VMALLOC_START) { pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; } __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, debug_pagealloc_enabled()); } static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end) { unsigned long kernel_start = __pa(_text); unsigned long kernel_end = __pa(__init_begin); /* * Take care not to create a writable alias for the * read-only text and rodata sections of the kernel image. */ /* No overlap with the kernel text/rodata */ if (end < kernel_start || start >= kernel_end) { __create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start, PAGE_KERNEL, early_pgtable_alloc, debug_pagealloc_enabled()); return; } /* * This block overlaps the kernel text/rodata mappings. * Map the portion(s) which don't overlap. */ if (start < kernel_start) __create_pgd_mapping(pgd, start, __phys_to_virt(start), kernel_start - start, PAGE_KERNEL, early_pgtable_alloc, debug_pagealloc_enabled()); if (kernel_end < end) __create_pgd_mapping(pgd, kernel_end, __phys_to_virt(kernel_end), end - kernel_end, PAGE_KERNEL, early_pgtable_alloc, debug_pagealloc_enabled()); /* * Map the linear alias of the [_text, __init_begin) interval as * read-only/non-executable. This makes the contents of the * region accessible to subsystems such as hibernate, but * protects it from inadvertent modification or execution. */ __create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start), kernel_end - kernel_start, PAGE_KERNEL_RO, early_pgtable_alloc, debug_pagealloc_enabled()); } static void __init map_mem(pgd_t *pgd) { struct memblock_region *reg; /* map all the memory banks */ for_each_memblock(memory, reg) { phys_addr_t start = reg->base; phys_addr_t end = start + reg->size; if (start >= end) break; if (memblock_is_nomap(reg)) continue; __map_memblock(pgd, start, end); } } void mark_rodata_ro(void) { unsigned long section_size; section_size = (unsigned long)_etext - (unsigned long)_text; create_mapping_late(__pa(_text), (unsigned long)_text, section_size, PAGE_KERNEL_ROX); /* * mark .rodata as read only. Use __init_begin rather than __end_rodata * to cover NOTES and EXCEPTION_TABLE. */ section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata; create_mapping_late(__pa(__start_rodata), (unsigned long)__start_rodata, section_size, PAGE_KERNEL_RO); /* flush the TLBs after updating live kernel mappings */ flush_tlb_all(); debug_checkwx(); } static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, pgprot_t prot, struct vm_struct *vma) { phys_addr_t pa_start = __pa(va_start); unsigned long size = va_end - va_start; BUG_ON(!PAGE_ALIGNED(pa_start)); BUG_ON(!PAGE_ALIGNED(size)); __create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot, early_pgtable_alloc, debug_pagealloc_enabled()); vma->addr = va_start; vma->phys_addr = pa_start; vma->size = size; vma->flags = VM_MAP; vma->caller = __builtin_return_address(0); vm_area_add_early(vma); } /* * Create fine-grained mappings for the kernel. */ static void __init map_kernel(pgd_t *pgd) { static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_init, vmlinux_data; map_kernel_segment(pgd, _text, _etext, PAGE_KERNEL_EXEC, &vmlinux_text); map_kernel_segment(pgd, __start_rodata, __init_begin, PAGE_KERNEL, &vmlinux_rodata); map_kernel_segment(pgd, __init_begin, __init_end, PAGE_KERNEL_EXEC, &vmlinux_init); map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data); if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) { /* * The fixmap falls in a separate pgd to the kernel, and doesn't * live in the carveout for the swapper_pg_dir. We can simply * re-use the existing dir for the fixmap. */ set_pgd(pgd_offset_raw(pgd, FIXADDR_START), *pgd_offset_k(FIXADDR_START)); } else if (CONFIG_PGTABLE_LEVELS > 3) { /* * The fixmap shares its top level pgd entry with the kernel * mapping. This can really only occur when we are running * with 16k/4 levels, so we can simply reuse the pud level * entry instead. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); set_pud(pud_set_fixmap_offset(pgd, FIXADDR_START), __pud(__pa(bm_pmd) | PUD_TYPE_TABLE)); pud_clear_fixmap(); } else { BUG(); } kasan_copy_shadow(pgd); } /* * paging_init() sets up the page tables, initialises the zone memory * maps and sets up the zero page. */ void __init paging_init(void) { phys_addr_t pgd_phys = early_pgtable_alloc(); pgd_t *pgd = pgd_set_fixmap(pgd_phys); map_kernel(pgd); map_mem(pgd); /* * We want to reuse the original swapper_pg_dir so we don't have to * communicate the new address to non-coherent secondaries in * secondary_entry, and so cpu_switch_mm can generate the address with * adrp+add rather than a load from some global variable. * * To do this we need to go via a temporary pgd. */ cpu_replace_ttbr1(__va(pgd_phys)); memcpy(swapper_pg_dir, pgd, PAGE_SIZE); cpu_replace_ttbr1(swapper_pg_dir); pgd_clear_fixmap(); memblock_free(pgd_phys, PAGE_SIZE); /* * We only reuse the PGD from the swapper_pg_dir, not the pud + pmd * allocated with it. */ memblock_free(__pa(swapper_pg_dir) + PAGE_SIZE, SWAPPER_DIR_SIZE - PAGE_SIZE); } /* * Check whether a kernel address is valid (derived from arch/x86/). */ int kern_addr_valid(unsigned long addr) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; if ((((long)addr) >> VA_BITS) != -1UL) return 0; pgd = pgd_offset_k(addr); if (pgd_none(*pgd)) return 0; pud = pud_offset(pgd, addr); if (pud_none(*pud)) return 0; if (pud_sect(*pud)) return pfn_valid(pud_pfn(*pud)); pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return 0; if (pmd_sect(*pmd)) return pfn_valid(pmd_pfn(*pmd)); pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) return 0; return pfn_valid(pte_pfn(*pte)); } #ifdef CONFIG_SPARSEMEM_VMEMMAP #if !ARM64_SWAPPER_USES_SECTION_MAPS int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { return vmemmap_populate_basepages(start, end, node); } #else /* !ARM64_SWAPPER_USES_SECTION_MAPS */ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { unsigned long addr = start; unsigned long next; pgd_t *pgd; pud_t *pud; pmd_t *pmd; do { next = pmd_addr_end(addr, end); pgd = vmemmap_pgd_populate(addr, node); if (!pgd) return -ENOMEM; pud = vmemmap_pud_populate(pgd, addr, node); if (!pud) return -ENOMEM; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { void *p = NULL; p = vmemmap_alloc_block_buf(PMD_SIZE, node); if (!p) return -ENOMEM; set_pmd(pmd, __pmd(__pa(p) | PROT_SECT_NORMAL)); } else vmemmap_verify((pte_t *)pmd, node, addr, next); } while (addr = next, addr != end); return 0; } #endif /* CONFIG_ARM64_64K_PAGES */ void vmemmap_free(unsigned long start, unsigned long end) { } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ static inline pud_t * fixmap_pud(unsigned long addr) { pgd_t *pgd = pgd_offset_k(addr); BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd)); return pud_offset_kimg(pgd, addr); } static inline pmd_t * fixmap_pmd(unsigned long addr) { pud_t *pud = fixmap_pud(addr); BUG_ON(pud_none(*pud) || pud_bad(*pud)); return pmd_offset_kimg(pud, addr); } static inline pte_t * fixmap_pte(unsigned long addr) { return &bm_pte[pte_index(addr)]; } void __init early_fixmap_init(void) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; unsigned long addr = FIXADDR_START; pgd = pgd_offset_k(addr); if (CONFIG_PGTABLE_LEVELS > 3 && !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa(bm_pud))) { /* * We only end up here if the kernel mapping and the fixmap * share the top level pgd entry, which should only happen on * 16k/4 levels configurations. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); pud = pud_offset_kimg(pgd, addr); } else { pgd_populate(&init_mm, pgd, bm_pud); pud = fixmap_pud(addr); } pud_populate(&init_mm, pud, bm_pmd); pmd = fixmap_pmd(addr); pmd_populate_kernel(&init_mm, pmd, bm_pte); /* * The boot-ioremap range spans multiple pmds, for which * we are not prepared: */ BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT) != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT)); if ((pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN))) || pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) { WARN_ON(1); pr_warn("pmd %p != %p, %p\n", pmd, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)), fixmap_pmd(fix_to_virt(FIX_BTMAP_END))); pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n", fix_to_virt(FIX_BTMAP_BEGIN)); pr_warn("fix_to_virt(FIX_BTMAP_END): %08lx\n", fix_to_virt(FIX_BTMAP_END)); pr_warn("FIX_BTMAP_END: %d\n", FIX_BTMAP_END); pr_warn("FIX_BTMAP_BEGIN: %d\n", FIX_BTMAP_BEGIN); } } void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); pte_t *pte; BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); pte = fixmap_pte(addr); if (pgprot_val(flags)) { set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); } else { pte_clear(&init_mm, addr, pte); flush_tlb_kernel_range(addr, addr+PAGE_SIZE); } } void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); int offset; void *dt_virt; /* * Check whether the physical FDT address is set and meets the minimum * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be * at least 8 bytes so that we can always access the magic and size * fields of the FDT header after mapping the first chunk, double check * here if that is indeed the case. */ BUILD_BUG_ON(MIN_FDT_ALIGN < 8); if (!dt_phys || dt_phys % MIN_FDT_ALIGN) return NULL; /* * Make sure that the FDT region can be mapped without the need to * allocate additional translation table pages, so that it is safe * to call create_mapping_noalloc() this early. * * On 64k pages, the FDT will be mapped using PTEs, so we need to * be in the same PMD as the rest of the fixmap. * On 4k pages, we'll use section mappings for the FDT so we only * have to be in the same PUD. */ BUILD_BUG_ON(dt_virt_base % SZ_2M); BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> SWAPPER_TABLE_SHIFT != __fix_to_virt(FIX_BTMAP_BEGIN) >> SWAPPER_TABLE_SHIFT); offset = dt_phys % SWAPPER_BLOCK_SIZE; dt_virt = (void *)dt_virt_base + offset; /* map the first chunk so we can read the size from the header */ create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, SWAPPER_BLOCK_SIZE, prot); if (fdt_magic(dt_virt) != FDT_MAGIC) return NULL; *size = fdt_totalsize(dt_virt); if (*size > MAX_FDT_SIZE) return NULL; if (offset + *size > SWAPPER_BLOCK_SIZE) create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, round_up(offset + *size, SWAPPER_BLOCK_SIZE), prot); return dt_virt; } void *__init fixmap_remap_fdt(phys_addr_t dt_phys) { void *dt_virt; int size; dt_virt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO); if (!dt_virt) return NULL; memblock_reserve(dt_phys, size); return dt_virt; } int __init arch_ioremap_pud_supported(void) { /* only 4k granule supports level 1 block mappings */ return IS_ENABLED(CONFIG_ARM64_4K_PAGES); } int __init arch_ioremap_pmd_supported(void) { return 1; } int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) { BUG_ON(phys & ~PUD_MASK); set_pud(pud, __pud(phys | PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot)))); return 1; } int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot) { BUG_ON(phys & ~PMD_MASK); set_pmd(pmd, __pmd(phys | PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot)))); return 1; } int pud_clear_huge(pud_t *pud) { if (!pud_sect(*pud)) return 0; pud_clear(pud); return 1; } int pmd_clear_huge(pmd_t *pmd) { if (!pmd_sect(*pmd)) return 0; pmd_clear(pmd); return 1; }