/* * * Copyright (C) 1995 Linus Torvalds * * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 */ /*################################################################### #Includes Intel Corporation's changes/modifications dated: 07/2011. #Changed/modified portions - Copyright(c) 2011, Intel Corporation. ###################################################################*/ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #ifdef CONFIG_ARCH_GEN3 #include #endif #ifdef CONFIG_ARCH_GEN3 #define GBE_CONFIG_RAM_BASE 0x60000 #define GBE_CONFIG_DATA_LENGTH 0x200 /* from $(KERNEL)/drivers/net/e1000/gbe_mac_access.h */ #define ACPI_RAM_BASE 0x10000 #define ACPI_DATA_LENGTH 0x8000 #define INTEL_8051_RAM_BASE 0x40000 #define INTEL_8051_DATA_LENGTH 0x10000 #endif unsigned long highstart_pfn, highend_pfn; static noinline int do_test_wp_bit(void); bool __read_mostly __vmalloc_start_set = false; static __init void *alloc_low_page(void) { unsigned long pfn = pgt_buf_end++; void *adr; if (pfn >= pgt_buf_top) panic("alloc_low_page: ran out of memory"); adr = __va(pfn * PAGE_SIZE); clear_page(adr); return adr; } /* * Creates a middle page table and puts a pointer to it in the * given global directory entry. This only returns the gd entry * in non-PAE compilation mode, since the middle layer is folded. */ static pmd_t * __init one_md_table_init(pgd_t *pgd) { pud_t *pud; pmd_t *pmd_table; #ifdef CONFIG_X86_PAE if (!(pgd_val(*pgd) & _PAGE_PRESENT)) { if (after_bootmem) pmd_table = (pmd_t *)alloc_bootmem_pages(PAGE_SIZE); else pmd_table = (pmd_t *)alloc_low_page(); paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT); set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); pud = pud_offset(pgd, 0); BUG_ON(pmd_table != pmd_offset(pud, 0)); return pmd_table; } #endif pud = pud_offset(pgd, 0); pmd_table = pmd_offset(pud, 0); return pmd_table; } /* * Create a page table and place a pointer to it in a middle page * directory entry: */ static pte_t * __init one_page_table_init(pmd_t *pmd) { if (!(pmd_val(*pmd) & _PAGE_PRESENT)) { pte_t *page_table = NULL; if (after_bootmem) { #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK) page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE); #endif if (!page_table) page_table = (pte_t *)alloc_bootmem_pages(PAGE_SIZE); } else page_table = (pte_t *)alloc_low_page(); paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE)); BUG_ON(page_table != pte_offset_kernel(pmd, 0)); } return pte_offset_kernel(pmd, 0); } pmd_t * __init populate_extra_pmd(unsigned long vaddr) { int pgd_idx = pgd_index(vaddr); int pmd_idx = pmd_index(vaddr); return one_md_table_init(swapper_pg_dir + pgd_idx) + pmd_idx; } pte_t * __init populate_extra_pte(unsigned long vaddr) { int pte_idx = pte_index(vaddr); pmd_t *pmd; pmd = populate_extra_pmd(vaddr); return one_page_table_init(pmd) + pte_idx; } static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd, unsigned long vaddr, pte_t *lastpte) { #ifdef CONFIG_HIGHMEM /* * Something (early fixmap) may already have put a pte * page here, which causes the page table allocation * to become nonlinear. Attempt to fix it, and if it * is still nonlinear then we have to bug. */ int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT; int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT; if (pmd_idx_kmap_begin != pmd_idx_kmap_end && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end && ((__pa(pte) >> PAGE_SHIFT) < pgt_buf_start || (__pa(pte) >> PAGE_SHIFT) >= pgt_buf_end)) { pte_t *newpte; int i; BUG_ON(after_bootmem); newpte = alloc_low_page(); for (i = 0; i < PTRS_PER_PTE; i++) set_pte(newpte + i, pte[i]); paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE)); BUG_ON(newpte != pte_offset_kernel(pmd, 0)); __flush_tlb_all(); paravirt_release_pte(__pa(pte) >> PAGE_SHIFT); pte = newpte; } BUG_ON(vaddr < fix_to_virt(FIX_KMAP_BEGIN - 1) && vaddr > fix_to_virt(FIX_KMAP_END) && lastpte && lastpte + PTRS_PER_PTE != pte); #endif return pte; } /* * This function initializes a certain range of kernel virtual memory * with new bootmem page tables, everywhere page tables are missing in * the given range. * * NOTE: The pagetables are allocated contiguous on the physical space * so we can cache the place of the first one and move around without * checking the pgd every time. */ static void __init page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) { int pgd_idx, pmd_idx; unsigned long vaddr; pgd_t *pgd; pmd_t *pmd; pte_t *pte = NULL; vaddr = start; pgd_idx = pgd_index(vaddr); pmd_idx = pmd_index(vaddr); pgd = pgd_base + pgd_idx; for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) { pmd = one_md_table_init(pgd); pmd = pmd + pmd_index(vaddr); for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); pmd++, pmd_idx++) { pte = page_table_kmap_check(one_page_table_init(pmd), pmd, vaddr, pte); vaddr += PMD_SIZE; } pmd_idx = 0; } } static inline int is_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end) return 1; return 0; } /* * This maps the physical memory to kernel virtual address space, a total * of max_low_pfn pages, by creating page tables starting from address * PAGE_OFFSET: */ unsigned long __init kernel_physical_mapping_init(unsigned long start, unsigned long end, unsigned long page_size_mask) { int use_pse = page_size_mask == (1<> PAGE_SHIFT; end_pfn = end >> PAGE_SHIFT; /* * First iteration will setup identity mapping using large/small pages * based on use_pse, with other attributes same as set by * the early code in head_32.S * * Second iteration will setup the appropriate attributes (NX, GLOBAL..) * as desired for the kernel identity mapping. * * This two pass mechanism conforms to the TLB app note which says: * * "Software should not write to a paging-structure entry in a way * that would change, for any linear address, both the page size * and either the page frame or attributes." */ mapping_iter = 1; if (!cpu_has_pse) use_pse = 0; repeat: pages_2m = pages_4k = 0; pfn = start_pfn; pgd_idx = pgd_index((pfn<= end_pfn) continue; #ifdef CONFIG_X86_PAE pmd_idx = pmd_index((pfn<> PAGE_SHIFT); } void __init native_pagetable_setup_done(pgd_t *base) { } /* * Build a proper pagetable for the kernel mappings. Up until this * point, we've been running on some set of pagetables constructed by * the boot process. * * If we're booting on native hardware, this will be a pagetable * constructed in arch/x86/kernel/head_32.S. The root of the * pagetable will be swapper_pg_dir. * * If we're booting paravirtualized under a hypervisor, then there are * more options: we may already be running PAE, and the pagetable may * or may not be based in swapper_pg_dir. In any case, * paravirt_pagetable_setup_start() will set up swapper_pg_dir * appropriately for the rest of the initialization to work. * * In general, pagetable_init() assumes that the pagetable may already * be partially populated, and so it avoids stomping on any existing * mappings. */ void __init early_ioremap_page_table_range_init(void) { pgd_t *pgd_base = swapper_pg_dir; unsigned long vaddr, end; /* * Fixed mappings, only the page table structure has to be * created - mappings will be set by set_fixmap(): */ vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK; page_table_range_init(vaddr, end, pgd_base); early_ioremap_reset(); } static void __init pagetable_init(void) { pgd_t *pgd_base = swapper_pg_dir; permanent_kmaps_init(pgd_base); } pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP); EXPORT_SYMBOL_GPL(__supported_pte_mask); /* user-defined highmem size */ static unsigned int highmem_pages = -1; /* * highmem=size forces highmem to be exactly 'size' bytes. * This works even on boxes that have no highmem otherwise. * This also works to reduce highmem size on bigger boxes. */ static int __init parse_highmem(char *arg) { if (!arg) return -EINVAL; highmem_pages = memparse(arg, &arg) >> PAGE_SHIFT; return 0; } early_param("highmem", parse_highmem); #define MSG_HIGHMEM_TOO_BIG \ "highmem size (%luMB) is bigger than pages available (%luMB)!\n" #define MSG_LOWMEM_TOO_SMALL \ "highmem size (%luMB) results in <64MB lowmem, ignoring it!\n" /* * All of RAM fits into lowmem - but if user wants highmem * artificially via the highmem=x boot parameter then create * it: */ void __init lowmem_pfn_init(void) { /* max_low_pfn is 0, we already have early_res support */ max_low_pfn = max_pfn; if (highmem_pages == -1) highmem_pages = 0; #ifdef CONFIG_HIGHMEM if (highmem_pages >= max_pfn) { printk(KERN_ERR MSG_HIGHMEM_TOO_BIG, pages_to_mb(highmem_pages), pages_to_mb(max_pfn)); highmem_pages = 0; } if (highmem_pages) { if (max_low_pfn - highmem_pages < 64*1024*1024/PAGE_SIZE) { printk(KERN_ERR MSG_LOWMEM_TOO_SMALL, pages_to_mb(highmem_pages)); highmem_pages = 0; } max_low_pfn -= highmem_pages; } #else if (highmem_pages) printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n"); #endif } #define MSG_HIGHMEM_TOO_SMALL \ "only %luMB highmem pages available, ignoring highmem size of %luMB!\n" #define MSG_HIGHMEM_TRIMMED \ "Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n" /* * We have more RAM than fits into lowmem - we try to put it into * highmem, also taking the highmem=x boot parameter into account: */ void __init highmem_pfn_init(void) { max_low_pfn = MAXMEM_PFN; if (highmem_pages == -1) highmem_pages = max_pfn - MAXMEM_PFN; if (highmem_pages + MAXMEM_PFN < max_pfn) max_pfn = MAXMEM_PFN + highmem_pages; if (highmem_pages + MAXMEM_PFN > max_pfn) { printk(KERN_WARNING MSG_HIGHMEM_TOO_SMALL, pages_to_mb(max_pfn - MAXMEM_PFN), pages_to_mb(highmem_pages)); highmem_pages = 0; } #ifndef CONFIG_HIGHMEM /* Maximum memory usable is what is directly addressable */ printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20); if (max_pfn > MAX_NONPAE_PFN) printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n"); else printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); max_pfn = MAXMEM_PFN; #else /* !CONFIG_HIGHMEM */ #ifndef CONFIG_HIGHMEM64G if (max_pfn > MAX_NONPAE_PFN) { max_pfn = MAX_NONPAE_PFN; printk(KERN_WARNING MSG_HIGHMEM_TRIMMED); } #endif /* !CONFIG_HIGHMEM64G */ #endif /* !CONFIG_HIGHMEM */ } /* * Determine low and high memory ranges: */ void __init find_low_pfn_range(void) { /* it could update max_pfn */ if (max_pfn <= MAXMEM_PFN) lowmem_pfn_init(); else highmem_pfn_init(); } #ifndef CONFIG_NEED_MULTIPLE_NODES void __init initmem_init(void) { #ifdef CONFIG_HIGHMEM highstart_pfn = highend_pfn = max_pfn; if (max_pfn > max_low_pfn) highstart_pfn = max_low_pfn; memblock_x86_register_active_regions(0, 0, highend_pfn); sparse_memory_present_with_active_regions(0); printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", pages_to_mb(highend_pfn - highstart_pfn)); num_physpages = highend_pfn; high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; #else memblock_x86_register_active_regions(0, 0, max_low_pfn); sparse_memory_present_with_active_regions(0); num_physpages = max_low_pfn; high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; #endif #ifdef CONFIG_FLATMEM max_mapnr = num_physpages; #endif __vmalloc_start_set = true; printk(KERN_NOTICE "%ldMB LOWMEM available.\n", pages_to_mb(max_low_pfn)); setup_bootmem_allocator(); } #endif /* !CONFIG_NEED_MULTIPLE_NODES */ static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM max_zone_pfns[ZONE_HIGHMEM] = highend_pfn; #endif free_area_init_nodes(max_zone_pfns); } void __init setup_bootmem_allocator(void) { printk(KERN_INFO " mapped low ram: 0 - %08lx\n", max_pfn_mapped<> 10, reservedpages << (PAGE_SHIFT-10), datasize >> 10, initsize >> 10, totalhigh_pages << (PAGE_SHIFT-10)); printk(KERN_INFO "virtual kernel memory layout:\n" " fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n" #ifdef CONFIG_HIGHMEM " pkmap : 0x%08lx - 0x%08lx (%4ld kB)\n" #endif " vmalloc : 0x%08lx - 0x%08lx (%4ld MB)\n" " lowmem : 0x%08lx - 0x%08lx (%4ld MB)\n" " .init : 0x%08lx - 0x%08lx (%4ld kB)\n" " .data : 0x%08lx - 0x%08lx (%4ld kB)\n" " .text : 0x%08lx - 0x%08lx (%4ld kB)\n", FIXADDR_START, FIXADDR_TOP, (FIXADDR_TOP - FIXADDR_START) >> 10, #ifdef CONFIG_HIGHMEM PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE, (LAST_PKMAP*PAGE_SIZE) >> 10, #endif VMALLOC_START, VMALLOC_END, (VMALLOC_END - VMALLOC_START) >> 20, (unsigned long)__va(0), (unsigned long)high_memory, ((unsigned long)high_memory - (unsigned long)__va(0)) >> 20, (unsigned long)&__init_begin, (unsigned long)&__init_end, ((unsigned long)&__init_end - (unsigned long)&__init_begin) >> 10, (unsigned long)&_etext, (unsigned long)&_edata, ((unsigned long)&_edata - (unsigned long)&_etext) >> 10, (unsigned long)&_text, (unsigned long)&_etext, ((unsigned long)&_etext - (unsigned long)&_text) >> 10); /* * Check boundaries twice: Some fundamental inconsistencies can * be detected at build time already. */ #define __FIXADDR_TOP (-PAGE_SIZE) #ifdef CONFIG_HIGHMEM BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE > FIXADDR_START); BUILD_BUG_ON(VMALLOC_END > PKMAP_BASE); #endif #define high_memory (-128UL << 20) BUILD_BUG_ON(VMALLOC_START >= VMALLOC_END); #undef high_memory #undef __FIXADDR_TOP #ifdef CONFIG_HIGHMEM BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE > FIXADDR_START); BUG_ON(VMALLOC_END > PKMAP_BASE); #endif BUG_ON(VMALLOC_START >= VMALLOC_END); BUG_ON((unsigned long)high_memory > VMALLOC_START); if (boot_cpu_data.wp_works_ok < 0) test_wp_bit(); } #ifdef CONFIG_MEMORY_HOTPLUG int arch_add_memory(int nid, u64 start, u64 size) { struct pglist_data *pgdata = NODE_DATA(nid); struct zone *zone = pgdata->node_zones + ZONE_HIGHMEM; unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; return __add_pages(nid, zone, start_pfn, nr_pages); } #endif /* * This function cannot be __init, since exceptions don't work in that * section. Put this after the callers, so that it cannot be inlined. */ static noinline int do_test_wp_bit(void) { char tmp_reg; int flag; __asm__ __volatile__( " movb %0, %1 \n" "1: movb %1, %0 \n" " xorl %2, %2 \n" "2: \n" _ASM_EXTABLE(1b,2b) :"=m" (*(char *)fix_to_virt(FIX_WP_TEST)), "=q" (tmp_reg), "=r" (flag) :"2" (1) :"memory"); return flag; } #ifdef CONFIG_DEBUG_RODATA const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); int kernel_set_to_readonly __read_mostly; void set_kernel_text_rw(void) { unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; if (!kernel_set_to_readonly) return; pr_debug("Set kernel text: %lx - %lx for read write\n", start, start+size); set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT); } void set_kernel_text_ro(void) { unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; if (!kernel_set_to_readonly) return; pr_debug("Set kernel text: %lx - %lx for read only\n", start, start+size); set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); } static void mark_nxdata_nx(void) { /* * When this called, init has already been executed and released, * so everything past _etext should be NX. */ unsigned long start = PFN_ALIGN(_etext); /* * This comes from is_kernel_text upper limit. Also HPAGE where used: */ unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start; if (__supported_pte_mask & _PAGE_NX) printk(KERN_INFO "NX-protecting the kernel data: %luk\n", size >> 10); set_pages_nx(virt_to_page(start), size >> PAGE_SHIFT); } void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); printk(KERN_INFO "Write protecting the kernel text: %luk\n", size >> 10); kernel_set_to_readonly = 1; #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n", start, start+size); set_pages_rw(virt_to_page(start), size>>PAGE_SHIFT); printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT); #endif start += size; size = (unsigned long)__end_rodata - start; set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", size >> 10); rodata_test(); #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, start + size); set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT); printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); #endif mark_nxdata_nx(); } #endif