--- zzzz-none-000/linux-3.10.107/arch/arm64/mm/mmu.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/arm64/mm/mmu.c 2021-02-04 17:41:59.000000000 +0000 @@ -21,21 +21,29 @@ #include #include #include +#include #include #include #include #include #include +#include +#include #include +#include +#include #include #include #include #include +#include #include #include "mm.h" +u64 idmap_t0sz = TCR_T0SZ(VA_BITS); + /* * Empty_zero_page is a special page that is used for zero-initialized data * and COW. @@ -43,112 +51,6 @@ struct page *empty_zero_page; EXPORT_SYMBOL(empty_zero_page); -pgprot_t pgprot_default; -EXPORT_SYMBOL(pgprot_default); - -static pmdval_t prot_sect_kernel; - -struct cachepolicy { - const char policy[16]; - u64 mair; - u64 tcr; -}; - -static struct cachepolicy cache_policies[] __initdata = { - { - .policy = "uncached", - .mair = 0x44, /* inner, outer non-cacheable */ - .tcr = TCR_IRGN_NC | TCR_ORGN_NC, - }, { - .policy = "writethrough", - .mair = 0xaa, /* inner, outer write-through, read-allocate */ - .tcr = TCR_IRGN_WT | TCR_ORGN_WT, - }, { - .policy = "writeback", - .mair = 0xee, /* inner, outer write-back, read-allocate */ - .tcr = TCR_IRGN_WBnWA | TCR_ORGN_WBnWA, - } -}; - -/* - * These are useful for identifying cache coherency problems by allowing the - * cache or the cache and writebuffer to be turned off. It changes the Normal - * memory caching attributes in the MAIR_EL1 register. - */ -static int __init early_cachepolicy(char *p) -{ - int i; - u64 tmp; - - for (i = 0; i < ARRAY_SIZE(cache_policies); i++) { - int len = strlen(cache_policies[i].policy); - - if (memcmp(p, cache_policies[i].policy, len) == 0) - break; - } - if (i == ARRAY_SIZE(cache_policies)) { - pr_err("ERROR: unknown or unsupported cache policy: %s\n", p); - return 0; - } - - flush_cache_all(); - - /* - * Modify MT_NORMAL attributes in MAIR_EL1. - */ - asm volatile( - " mrs %0, mair_el1\n" - " bfi %0, %1, #%2, #8\n" - " msr mair_el1, %0\n" - " isb\n" - : "=&r" (tmp) - : "r" (cache_policies[i].mair), "i" (MT_NORMAL * 8)); - - /* - * Modify TCR PTW cacheability attributes. - */ - asm volatile( - " mrs %0, tcr_el1\n" - " bic %0, %0, %2\n" - " orr %0, %0, %1\n" - " msr tcr_el1, %0\n" - " isb\n" - : "=&r" (tmp) - : "r" (cache_policies[i].tcr), "r" (TCR_IRGN_MASK | TCR_ORGN_MASK)); - - flush_cache_all(); - - return 0; -} -early_param("cachepolicy", early_cachepolicy); - -/* - * Adjust the PMD section entries according to the CPU in use. - */ -static void __init init_mem_pgprot(void) -{ - pteval_t default_pgprot; - int i; - - default_pgprot = PTE_ATTRINDX(MT_NORMAL); - prot_sect_kernel = PMD_TYPE_SECT | PMD_SECT_AF | PMD_ATTRINDX(MT_NORMAL); - -#ifdef CONFIG_SMP - /* - * Mark memory with the "shared" attribute for SMP systems - */ - default_pgprot |= PTE_SHARED; - prot_sect_kernel |= PMD_SECT_S; -#endif - - for (i = 0; i < 16; i++) { - unsigned long v = pgprot_val(protection_map[i]); - protection_map[i] = __pgprot(v | default_pgprot); - } - - pgprot_default = __pgprot(PTE_TYPE_PAGE | PTE_AF | default_pgprot); -} - pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { @@ -162,31 +64,73 @@ static void __init *early_alloc(unsigned long sz) { - void *ptr = __va(memblock_alloc(sz, sz)); + phys_addr_t phys; + void *ptr; + + phys = memblock_alloc(sz, sz); + BUG_ON(!phys); + ptr = __va(phys); memset(ptr, 0, sz); return ptr; } -static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr, - unsigned long end, unsigned long pfn) +/* + * remap a PMD into pages + */ +static void split_pmd(pmd_t *pmd, pte_t *pte) +{ + unsigned long pfn = pmd_pfn(*pmd); + int i = 0; + + do { + /* + * Need to have the least restrictive permissions available + * permissions will be fixed up later + */ + set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC)); + pfn++; + } while (pte++, i++, i < PTRS_PER_PTE); +} + +static void alloc_init_pte(pmd_t *pmd, unsigned long addr, + unsigned long end, unsigned long pfn, + pgprot_t prot, + void *(*alloc)(unsigned long size)) { pte_t *pte; - if (pmd_none(*pmd)) { - pte = early_alloc(PTRS_PER_PTE * sizeof(pte_t)); + if (pmd_none(*pmd) || pmd_sect(*pmd)) { + pte = alloc(PTRS_PER_PTE * sizeof(pte_t)); + if (pmd_sect(*pmd)) + split_pmd(pmd, pte); __pmd_populate(pmd, __pa(pte), PMD_TYPE_TABLE); + flush_tlb_all(); } BUG_ON(pmd_bad(*pmd)); pte = pte_offset_kernel(pmd, addr); do { - set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC)); + set_pte(pte, pfn_pte(pfn, prot)); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); } -static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, - unsigned long end, phys_addr_t phys) +static void split_pud(pud_t *old_pud, pmd_t *pmd) +{ + unsigned long addr = pud_pfn(*old_pud) << PAGE_SHIFT; + pgprot_t prot = __pgprot(pud_val(*old_pud) ^ addr); + int i = 0; + + do { + set_pmd(pmd, __pmd(addr | pgprot_val(prot))); + addr += PMD_SIZE; + } while (pmd++, i++, i < PTRS_PER_PMD); +} + +static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + void *(*alloc)(unsigned long size)) { pmd_t *pmd; unsigned long next; @@ -194,10 +138,19 @@ /* * Check for initial section mappings in the pgd/pud and remove them. */ - if (pud_none(*pud) || pud_bad(*pud)) { - pmd = early_alloc(PTRS_PER_PMD * sizeof(pmd_t)); - pud_populate(&init_mm, pud, pmd); + if (pud_none(*pud) || pud_sect(*pud)) { + pmd = alloc(PTRS_PER_PMD * sizeof(pmd_t)); + if (pud_sect(*pud)) { + /* + * need to have the 1G of mappings continue to be + * present + */ + split_pud(pud, pmd); + } + pud_populate(mm, pud, pmd); + flush_tlb_all(); } + BUG_ON(pud_bad(*pud)); pmd = pmd_offset(pud, addr); do { @@ -205,29 +158,84 @@ /* try section mapping first */ if (((addr | next | phys) & ~SECTION_MASK) == 0) { pmd_t old_pmd =*pmd; - set_pmd(pmd, __pmd(phys | prot_sect_kernel)); + set_pmd(pmd, __pmd(phys | + pgprot_val(mk_sect_prot(prot)))); /* * Check for previous table entries created during * boot (__create_page_tables) and flush them. */ - if (!pmd_none(old_pmd)) + if (!pmd_none(old_pmd)) { flush_tlb_all(); + if (pmd_table(old_pmd)) { + phys_addr_t table = __pa(pte_offset_map(&old_pmd, 0)); + if (!WARN_ON_ONCE(slab_is_available())) + memblock_free(table, PAGE_SIZE); + } + } } else { - alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys)); + alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys), + prot, alloc); } phys += next - addr; } while (pmd++, addr = next, addr != end); } -static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, - unsigned long end, unsigned long phys) +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(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + void *(*alloc)(unsigned long size)) { - pud_t *pud = pud_offset(pgd, addr); + pud_t *pud; unsigned long next; + if (pgd_none(*pgd)) { + pud = alloc(PTRS_PER_PUD * sizeof(pud_t)); + pgd_populate(mm, pgd, pud); + } + BUG_ON(pgd_bad(*pgd)); + + pud = pud_offset(pgd, addr); do { next = pud_addr_end(addr, end); - alloc_init_pmd(pud, addr, next, phys); + + /* + * For 4K granule only, attempt to put down a 1GB block + */ + if (use_1G_block(addr, next, phys)) { + pud_t old_pud = *pud; + set_pud(pud, __pud(phys | + pgprot_val(mk_sect_prot(prot)))); + + /* + * If we have an old value for a pud, it will + * be pointing to a pmd table that we no longer + * need (from swapper_pg_dir). + * + * Look up the old pmd table and free it. + */ + if (!pud_none(old_pud)) { + flush_tlb_all(); + if (pud_table(old_pud)) { + phys_addr_t table = __pa(pmd_offset(&old_pud, 0)); + if (!WARN_ON_ONCE(slab_is_available())) + memblock_free(table, PAGE_SIZE); + } + } + } else { + alloc_init_pmd(mm, pud, addr, next, phys, prot, alloc); + } phys += next - addr; } while (pud++, addr = next, addr != end); } @@ -236,74 +244,126 @@ * Create the page directory entries and any necessary page tables for the * mapping specified by 'md'. */ -static void __init create_mapping(phys_addr_t phys, unsigned long virt, - phys_addr_t size) +static void __create_mapping(struct mm_struct *mm, pgd_t *pgd, + phys_addr_t phys, unsigned long virt, + phys_addr_t size, pgprot_t prot, + void *(*alloc)(unsigned long size)) { unsigned long addr, length, end, next; - pgd_t *pgd; - - if (virt < VMALLOC_START) { - pr_warning("BUG: not creating mapping for 0x%016llx at 0x%016lx - outside kernel range\n", - phys, virt); - return; - } addr = virt & PAGE_MASK; length = PAGE_ALIGN(size + (virt & ~PAGE_MASK)); - pgd = pgd_offset_k(addr); end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgd, addr, next, phys); + alloc_init_pud(mm, pgd, addr, next, phys, prot, alloc); phys += next - addr; } while (pgd++, addr = next, addr != end); } -#ifdef CONFIG_EARLY_PRINTK -/* - * Create an early I/O mapping using the pgd/pmd entries already populated - * in head.S as this function is called too early to allocated any memory. The - * mapping size is 2MB with 4KB pages or 64KB or 64KB pages. - */ -void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt) +static void *late_alloc(unsigned long size) { - unsigned long size, mask; - bool page64k = IS_ENABLED(CONFIG_ARM64_64K_PAGES); - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + void *ptr; + + BUG_ON(size > PAGE_SIZE); + ptr = (void *)__get_free_page(PGALLOC_GFP); + BUG_ON(!ptr); + return ptr; +} + +static void __init create_mapping(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_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), phys, virt, + size, prot, early_alloc); +} + +void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot) +{ + __create_mapping(mm, pgd_offset(mm, virt), phys, virt, size, prot, + late_alloc); +} + +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; + } + + return __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), + phys, virt, size, prot, late_alloc); +} +#ifdef CONFIG_DEBUG_RODATA +static void __init __map_memblock(phys_addr_t start, phys_addr_t end) +{ /* - * No early pte entries with !ARM64_64K_PAGES configuration, so using - * sections (pmd). + * Set up the executable regions using the existing section mappings + * for now. This will get more fine grained later once all memory + * is mapped */ - size = page64k ? PAGE_SIZE : SECTION_SIZE; - mask = ~(size - 1); + unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE); + unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE); - pgd = pgd_offset_k(virt); - pud = pud_offset(pgd, virt); - if (pud_none(*pud)) - return NULL; - pmd = pmd_offset(pud, virt); - - if (page64k) { - if (pmd_none(*pmd)) - return NULL; - pte = pte_offset_kernel(pmd, virt); - set_pte(pte, __pte((phys & mask) | PROT_DEVICE_nGnRE)); + if (end < kernel_x_start) { + create_mapping(start, __phys_to_virt(start), + end - start, PAGE_KERNEL); + } else if (start >= kernel_x_end) { + create_mapping(start, __phys_to_virt(start), + end - start, PAGE_KERNEL); } else { - set_pmd(pmd, __pmd((phys & mask) | PROT_SECT_DEVICE_nGnRE)); + if (start < kernel_x_start) + create_mapping(start, __phys_to_virt(start), + kernel_x_start - start, + PAGE_KERNEL); + create_mapping(kernel_x_start, + __phys_to_virt(kernel_x_start), + kernel_x_end - kernel_x_start, + PAGE_KERNEL_EXEC); + if (kernel_x_end < end) + create_mapping(kernel_x_end, + __phys_to_virt(kernel_x_end), + end - kernel_x_end, + PAGE_KERNEL); } - return (void __iomem *)((virt & mask) + (phys & ~mask)); +} +#else +static void __init __map_memblock(phys_addr_t start, phys_addr_t end) +{ + create_mapping(start, __phys_to_virt(start), end - start, + PAGE_KERNEL_EXEC); } #endif static void __init map_mem(void) { struct memblock_region *reg; + phys_addr_t limit; + + /* + * Temporarily limit the memblock range. We need to do this as + * create_mapping requires puds, pmds and ptes to be allocated from + * memory addressable from the initial direct kernel mapping. + * + * The initial direct kernel mapping, located at swapper_pg_dir, gives + * us PUD_SIZE (with SECTION maps) or PMD_SIZE (without SECTION maps, + * memory starting from PHYS_OFFSET (which must be aligned to 2MB as + * per Documentation/arm64/booting.txt). + */ + limit = PHYS_OFFSET + SWAPPER_INIT_MAP_SIZE; + memblock_set_current_limit(limit); /* map all the memory banks */ for_each_memblock(memory, reg) { @@ -313,8 +373,69 @@ if (start >= end) break; - create_mapping(start, __phys_to_virt(start), end - start); + if (ARM64_SWAPPER_USES_SECTION_MAPS) { + /* + * For the first memory bank align the start address and + * current memblock limit to prevent create_mapping() from + * allocating pte page tables from unmapped memory. With + * the section maps, if the first block doesn't end on section + * size boundary, create_mapping() will try to allocate a pte + * page, which may be returned from an unmapped area. + * When section maps are not used, the pte page table for the + * current limit is already present in swapper_pg_dir. + */ + if (start < limit) + start = ALIGN(start, SECTION_SIZE); + if (end < limit) { + limit = end & SECTION_MASK; + memblock_set_current_limit(limit); + } + } + __map_memblock(start, end); } + + /* Limit no longer required. */ + memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); +} + +static void __init fixup_executable(void) +{ +#ifdef CONFIG_DEBUG_RODATA + /* now that we are actually fully mapped, make the start/end more fine grained */ + if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) { + unsigned long aligned_start = round_down(__pa(_stext), + SWAPPER_BLOCK_SIZE); + + create_mapping(aligned_start, __phys_to_virt(aligned_start), + __pa(_stext) - aligned_start, + PAGE_KERNEL); + } + + if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) { + unsigned long aligned_end = round_up(__pa(__init_end), + SWAPPER_BLOCK_SIZE); + create_mapping(__pa(__init_end), (unsigned long)__init_end, + aligned_end - __pa(__init_end), + PAGE_KERNEL); + } +#endif +} + +#ifdef CONFIG_DEBUG_RODATA +void mark_rodata_ro(void) +{ + create_mapping_late(__pa(_stext), (unsigned long)_stext, + (unsigned long)_etext - (unsigned long)_stext, + PAGE_KERNEL_ROX); + +} +#endif + +void fixup_init(void) +{ + create_mapping_late(__pa(__init_begin), (unsigned long)__init_begin, + (unsigned long)__init_end - (unsigned long)__init_begin, + PAGE_KERNEL); } /* @@ -325,21 +446,8 @@ { void *zero_page; - /* - * Maximum PGDIR_SIZE addressable via the initial direct kernel - * mapping in swapper_pg_dir. - */ - memblock_set_current_limit((PHYS_OFFSET & PGDIR_MASK) + PGDIR_SIZE); - - init_mem_pgprot(); map_mem(); - - /* - * Finally flush the caches and tlb to ensure that we're in a - * consistent state. - */ - flush_cache_all(); - flush_tlb_all(); + fixup_executable(); /* allocate the zero page. */ zero_page = early_alloc(PAGE_SIZE); @@ -349,23 +457,15 @@ empty_zero_page = virt_to_page(zero_page); /* Ensure the zero page is visible to the page table walker */ - dsb(); + dsb(ishst); /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. */ cpu_set_reserved_ttbr0(); - flush_tlb_all(); -} - -/* - * Enable the identity mapping to allow the MMU disabling. - */ -void setup_mm_for_reboot(void) -{ - cpu_switch_mm(idmap_pg_dir, &init_mm); - flush_tlb_all(); + local_flush_tlb_all(); + cpu_set_default_tcr_t0sz(); } /* @@ -389,10 +489,16 @@ 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; @@ -400,12 +506,12 @@ return pfn_valid(pte_pfn(*pte)); } #ifdef CONFIG_SPARSEMEM_VMEMMAP -#ifdef CONFIG_ARM64_64K_PAGES +#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 /* !CONFIG_ARM64_64K_PAGES */ +#else /* !ARM64_SWAPPER_USES_SECTION_MAPS */ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { unsigned long addr = start; @@ -433,7 +539,7 @@ if (!p) return -ENOMEM; - set_pmd(pmd, __pmd(__pa(p) | prot_sect_kernel)); + set_pmd(pmd, __pmd(__pa(p) | PROT_SECT_NORMAL)); } else vmemmap_verify((pte_t *)pmd, node, addr, next); } while (addr = next, addr != end); @@ -445,3 +551,149 @@ { } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ + +static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss; +#if CONFIG_PGTABLE_LEVELS > 2 +static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss; +#endif +#if CONFIG_PGTABLE_LEVELS > 3 +static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss; +#endif + +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(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(pud, addr); +} + +static inline pte_t * fixmap_pte(unsigned long addr) +{ + pmd_t *pmd = fixmap_pmd(addr); + + BUG_ON(pmd_none(*pmd) || pmd_bad(*pmd)); + + return pte_offset_kernel(pmd, 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); + pgd_populate(&init_mm, pgd, bm_pud); + pud = pud_offset(pgd, addr); + pud_populate(&init_mm, pud, bm_pmd); + pmd = pmd_offset(pud, addr); + pmd_populate_kernel(&init_mm, pmd, bm_pte); + + /* + * The boot-ioremap range spans multiple pmds, for which + * we are not preparted: + */ + 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) +{ + const u64 dt_virt_base = __fix_to_virt(FIX_FDT); + pgprot_t prot = PAGE_KERNEL_RO; + int size, 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() 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(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(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, + round_up(offset + size, SWAPPER_BLOCK_SIZE), prot); + + memblock_reserve(dt_phys, size); + + return dt_virt; +}