diff options
Diffstat (limited to 'arch/x86/mm/init_32.c')
| -rw-r--r-- | arch/x86/mm/init_32.c | 817 |
1 files changed, 485 insertions, 332 deletions
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 9ec62da85fd..e39504878ae 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -21,18 +21,20 @@ #include <linux/init.h> #include <linux/highmem.h> #include <linux/pagemap.h> +#include <linux/pci.h> #include <linux/pfn.h> #include <linux/poison.h> #include <linux/bootmem.h> -#include <linux/slab.h> +#include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/memory_hotplug.h> #include <linux/initrd.h> #include <linux/cpumask.h> +#include <linux/gfp.h> #include <asm/asm.h> +#include <asm/bios_ebda.h> #include <asm/processor.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/dma.h> @@ -42,21 +44,23 @@ #include <asm/bugs.h> #include <asm/tlb.h> #include <asm/tlbflush.h> +#include <asm/olpc_ofw.h> #include <asm/pgalloc.h> #include <asm/sections.h> #include <asm/paravirt.h> #include <asm/setup.h> #include <asm/cacheflush.h> +#include <asm/page_types.h> +#include <asm/init.h> -unsigned int __VMALLOC_RESERVE = 128 << 20; +#include "mm_internal.h" -unsigned long max_pfn_mapped; - -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); unsigned long highstart_pfn, highend_pfn; static noinline int do_test_wp_bit(void); +bool __read_mostly __vmalloc_start_set = false; + /* * Creates a middle page table and puts a pointer to it in the * given global directory entry. This only returns the gd entry @@ -69,12 +73,13 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) #ifdef CONFIG_X86_PAE if (!(pgd_val(*pgd) & _PAGE_PRESENT)) { - pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE); - - paravirt_alloc_pd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT); + 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); @@ -90,17 +95,9 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) static pte_t * __init one_page_table_init(pmd_t *pmd) { if (!(pmd_val(*pmd) & _PAGE_PRESENT)) { - pte_t *page_table = NULL; + pte_t *page_table = (pte_t *)alloc_low_page(); -#ifdef CONFIG_DEBUG_PAGEALLOC - page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE); -#endif - if (!page_table) { - page_table = - (pte_t *)alloc_bootmem_low_pages(PAGE_SIZE); - } - - paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT); + 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)); } @@ -108,6 +105,94 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) 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 unsigned long __init +page_table_range_init_count(unsigned long start, unsigned long end) +{ + unsigned long count = 0; +#ifdef CONFIG_HIGHMEM + 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; + int pgd_idx, pmd_idx; + unsigned long vaddr; + + if (pmd_idx_kmap_begin == pmd_idx_kmap_end) + return 0; + + vaddr = start; + pgd_idx = pgd_index(vaddr); + + for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) { + for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); + pmd_idx++) { + if ((vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin && + (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end) + count++; + vaddr += PMD_SIZE; + } + pmd_idx = 0; + } +#endif + return count; +} + +static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd, + unsigned long vaddr, pte_t *lastpte, + void **adr) +{ +#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) { + pte_t *newpte; + int i; + + BUG_ON(after_bootmem); + newpte = *adr; + for (i = 0; i < PTRS_PER_PTE; i++) + set_pte(newpte + i, pte[i]); + *adr = (void *)(((unsigned long)(*adr)) + PAGE_SIZE); + + 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 @@ -124,6 +209,12 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) unsigned long vaddr; pgd_t *pgd; pmd_t *pmd; + pte_t *pte = NULL; + unsigned long count = page_table_range_init_count(start, end); + void *adr = NULL; + + if (count) + adr = alloc_low_pages(count); vaddr = start; pgd_idx = pgd_index(vaddr); @@ -135,7 +226,8 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) pmd = pmd + pmd_index(vaddr); for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); pmd++, pmd_idx++) { - one_page_table_init(pmd); + pte = page_table_kmap_check(one_page_table_init(pmd), + pmd, vaddr, pte, &adr); vaddr += PMD_SIZE; } @@ -145,7 +237,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) static inline int is_kernel_text(unsigned long addr) { - if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end) + if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end) return 1; return 0; } @@ -155,41 +247,81 @@ static inline int is_kernel_text(unsigned long addr) * of max_low_pfn pages, by creating page tables starting from address * PAGE_OFFSET: */ -static void __init kernel_physical_mapping_init(pgd_t *pgd_base) +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<<PG_LEVEL_2M); + unsigned long last_map_addr = end; + unsigned long start_pfn, end_pfn; + pgd_t *pgd_base = swapper_pg_dir; int pgd_idx, pmd_idx, pte_ofs; unsigned long pfn; pgd_t *pgd; pmd_t *pmd; pte_t *pte; + unsigned pages_2m, pages_4k; + int mapping_iter; - pgd_idx = pgd_index(PAGE_OFFSET); - pgd = pgd_base + pgd_idx; - pfn = 0; + start_pfn = start >> 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<<PAGE_SHIFT) + PAGE_OFFSET); + pgd = pgd_base + pgd_idx; for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) { pmd = one_md_table_init(pgd); - if (pfn >= max_low_pfn) - continue; - for (pmd_idx = 0; - pmd_idx < PTRS_PER_PMD && pfn < max_low_pfn; + if (pfn >= end_pfn) + continue; +#ifdef CONFIG_X86_PAE + pmd_idx = pmd_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET); + pmd += pmd_idx; +#else + pmd_idx = 0; +#endif + for (; pmd_idx < PTRS_PER_PMD && pfn < end_pfn; pmd++, pmd_idx++) { unsigned int addr = pfn * PAGE_SIZE + PAGE_OFFSET; /* * Map with big pages if possible, otherwise * create normal page tables: - * - * Don't use a large page for the first 2/4MB of memory - * because there are often fixed size MTRRs in there - * and overlapping MTRRs into large pages can cause - * slowdowns. */ - if (cpu_has_pse && !(pgd_idx == 0 && pmd_idx == 0)) { + if (use_pse) { unsigned int addr2; pgprot_t prot = PAGE_KERNEL_LARGE; - + /* + * first pass will use the same initial + * identity mapping attribute + _PAGE_PSE. + */ + pgprot_t init_prot = + __pgprot(PTE_IDENT_ATTR | + _PAGE_PSE); + + pfn &= PMD_MASK >> PAGE_SHIFT; addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE + PAGE_OFFSET + PAGE_SIZE-1; @@ -197,37 +329,63 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base) is_kernel_text(addr2)) prot = PAGE_KERNEL_LARGE_EXEC; - set_pmd(pmd, pfn_pmd(pfn, prot)); + pages_2m++; + if (mapping_iter == 1) + set_pmd(pmd, pfn_pmd(pfn, init_prot)); + else + set_pmd(pmd, pfn_pmd(pfn, prot)); pfn += PTRS_PER_PTE; - max_pfn_mapped = pfn; continue; } pte = one_page_table_init(pmd); - for (pte_ofs = 0; - pte_ofs < PTRS_PER_PTE && pfn < max_low_pfn; + pte_ofs = pte_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET); + pte += pte_ofs; + for (; pte_ofs < PTRS_PER_PTE && pfn < end_pfn; pte++, pfn++, pte_ofs++, addr += PAGE_SIZE) { pgprot_t prot = PAGE_KERNEL; + /* + * first pass will use the same initial + * identity mapping attribute. + */ + pgprot_t init_prot = __pgprot(PTE_IDENT_ATTR); if (is_kernel_text(addr)) prot = PAGE_KERNEL_EXEC; - set_pte(pte, pfn_pte(pfn, prot)); + pages_4k++; + if (mapping_iter == 1) { + set_pte(pte, pfn_pte(pfn, init_prot)); + last_map_addr = (pfn << PAGE_SHIFT) + PAGE_SIZE; + } else + set_pte(pte, pfn_pte(pfn, prot)); } - max_pfn_mapped = pfn; } } -} + if (mapping_iter == 1) { + /* + * update direct mapping page count only in the first + * iteration. + */ + update_page_count(PG_LEVEL_2M, pages_2m); + update_page_count(PG_LEVEL_4K, pages_4k); -static inline int page_kills_ppro(unsigned long pagenr) -{ - if (pagenr >= 0x70000 && pagenr <= 0x7003F) - return 1; - return 0; + /* + * local global flush tlb, which will flush the previous + * mappings present in both small and large page TLB's. + */ + __flush_tlb_all(); + + /* + * Second iteration will set the actual desired PTE attributes. + */ + mapping_iter = 2; + goto repeat; + } + return last_map_addr; } -#ifdef CONFIG_HIGHMEM pte_t *kmap_pte; pgprot_t kmap_prot; @@ -250,6 +408,7 @@ static void __init kmap_init(void) kmap_prot = PAGE_KERNEL; } +#ifdef CONFIG_HIGHMEM static void __init permanent_kmaps_init(pgd_t *pgd_base) { unsigned long vaddr; @@ -268,87 +427,46 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) pkmap_page_table = pte; } -static void __meminit free_new_highpage(struct page *page) -{ - init_page_count(page); - __free_page(page); - totalhigh_pages++; -} - -void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro) +void __init add_highpages_with_active_regions(int nid, + unsigned long start_pfn, unsigned long end_pfn) { - if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) { - ClearPageReserved(page); - free_new_highpage(page); - } else - SetPageReserved(page); -} - -static int __meminit -add_one_highpage_hotplug(struct page *page, unsigned long pfn) -{ - free_new_highpage(page); - totalram_pages++; -#ifdef CONFIG_FLATMEM - max_mapnr = max(pfn, max_mapnr); -#endif - num_physpages++; - - return 0; -} - -/* - * Not currently handling the NUMA case. - * Assuming single node and all memory that - * has been added dynamically that would be - * onlined here is in HIGHMEM. - */ -void __meminit online_page(struct page *page) -{ - ClearPageReserved(page); - add_one_highpage_hotplug(page, page_to_pfn(page)); -} - -#ifndef CONFIG_NUMA -static void __init set_highmem_pages_init(int bad_ppro) -{ - int pfn; - - for (pfn = highstart_pfn; pfn < highend_pfn; pfn++) { - /* - * Holes under sparsemem might not have no mem_map[]: - */ - if (pfn_valid(pfn)) - add_one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro); + phys_addr_t start, end; + u64 i; + + for_each_free_mem_range(i, nid, &start, &end, NULL) { + unsigned long pfn = clamp_t(unsigned long, PFN_UP(start), + start_pfn, end_pfn); + unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end), + start_pfn, end_pfn); + for ( ; pfn < e_pfn; pfn++) + if (pfn_valid(pfn)) + free_highmem_page(pfn_to_page(pfn)); } - totalram_pages += totalhigh_pages; } -#endif /* !CONFIG_NUMA */ - #else -# define kmap_init() do { } while (0) -# define permanent_kmaps_init(pgd_base) do { } while (0) -# define set_highmem_pages_init(bad_ppro) do { } while (0) +static inline void permanent_kmaps_init(pgd_t *pgd_base) +{ +} #endif /* CONFIG_HIGHMEM */ -pteval_t __PAGE_KERNEL = _PAGE_KERNEL; -EXPORT_SYMBOL(__PAGE_KERNEL); - -pteval_t __PAGE_KERNEL_EXEC = _PAGE_KERNEL_EXEC; - -void __init native_pagetable_setup_start(pgd_t *base) +void __init native_pagetable_init(void) { unsigned long pfn, va; - pgd_t *pgd; + pgd_t *pgd, *base = swapper_pg_dir; pud_t *pud; pmd_t *pmd; pte_t *pte; /* * Remove any mappings which extend past the end of physical - * memory from the boot time page table: + * memory from the boot time page table. + * In virtual address space, we should have at least two pages + * from VMALLOC_END to pkmap or fixmap according to VMALLOC_END + * definition. And max_low_pfn is set to VMALLOC_END physical + * address. If initial memory mapping is doing right job, we + * should have pte used near max_low_pfn or one pmd is not present. */ - for (pfn = max_low_pfn + 1; pfn < 1<<(32-PAGE_SHIFT); pfn++) { + for (pfn = max_low_pfn; pfn < 1<<(32-PAGE_SHIFT); pfn++) { va = PAGE_OFFSET + (pfn<<PAGE_SHIFT); pgd = base + pgd_index(va); if (!pgd_present(*pgd)) @@ -359,17 +477,23 @@ void __init native_pagetable_setup_start(pgd_t *base) if (!pmd_present(*pmd)) break; + /* should not be large page here */ + if (pmd_large(*pmd)) { + pr_warn("try to clear pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx, but pmd is big page and is not using pte !\n", + pfn, pmd, __pa(pmd)); + BUG_ON(1); + } + pte = pte_offset_kernel(pmd, va); if (!pte_present(*pte)) break; + printk(KERN_DEBUG "clearing pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx pte: %p pte phys: %lx\n", + pfn, pmd, __pa(pmd), pte, __pa(pte)); pte_clear(NULL, va, pte); } - paravirt_alloc_pd(&init_mm, __pa(base) >> PAGE_SHIFT); -} - -void __init native_pagetable_setup_done(pgd_t *base) -{ + paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT); + paging_init(); } /* @@ -384,143 +508,184 @@ void __init native_pagetable_setup_done(pgd_t *base) * 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 + * paravirt_pagetable_init() 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. */ -static void __init pagetable_init(void) +void __init early_ioremap_page_table_range_init(void) { pgd_t *pgd_base = swapper_pg_dir; unsigned long vaddr, end; - paravirt_pagetable_setup_start(pgd_base); - - /* Enable PSE if available */ - if (cpu_has_pse) - set_in_cr4(X86_CR4_PSE); - - /* Enable PGE if available */ - if (cpu_has_pge) { - set_in_cr4(X86_CR4_PGE); - __PAGE_KERNEL |= _PAGE_GLOBAL; - __PAGE_KERNEL_EXEC |= _PAGE_GLOBAL; - } - - kernel_physical_mapping_init(pgd_base); - remap_numa_kva(); - /* * Fixed mappings, only the page table structure has to be * created - mappings will be set by set_fixmap(): */ - early_ioremap_clear(); 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(); +} - permanent_kmaps_init(pgd_base); +static void __init pagetable_init(void) +{ + pgd_t *pgd_base = swapper_pg_dir; - paravirt_pagetable_setup_done(pgd_base); + permanent_kmaps_init(pgd_base); } -#ifdef CONFIG_ACPI_SLEEP +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; + /* - * ACPI suspend needs this for resume, because things like the intel-agp - * driver might have split up a kernel 4MB mapping. + * 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. */ -char swsusp_pg_dir[PAGE_SIZE] - __attribute__ ((aligned(PAGE_SIZE))); - -static inline void save_pg_dir(void) -{ - memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE); -} -#else /* !CONFIG_ACPI_SLEEP */ -static inline void save_pg_dir(void) +static int __init parse_highmem(char *arg) { + if (!arg) + return -EINVAL; + + highmem_pages = memparse(arg, &arg) >> PAGE_SHIFT; + return 0; } -#endif /* !CONFIG_ACPI_SLEEP */ +early_param("highmem", parse_highmem); -void zap_low_mappings(void) -{ - int i; +#define MSG_HIGHMEM_TOO_BIG \ + "highmem size (%luMB) is bigger than pages available (%luMB)!\n" - save_pg_dir(); +#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: + */ +static void __init lowmem_pfn_init(void) +{ + /* max_low_pfn is 0, we already have early_res support */ + max_low_pfn = max_pfn; - /* - * Zap initial low-memory mappings. - * - * Note that "pgd_clear()" doesn't do it for - * us, because pgd_clear() is a no-op on i386. - */ - for (i = 0; i < USER_PTRS_PER_PGD; i++) { -#ifdef CONFIG_X86_PAE - set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page))); + 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 - set_pgd(swapper_pg_dir+i, __pgd(0)); + if (highmem_pages) + printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n"); #endif - } - flush_tlb_all(); } -int nx_enabled; +#define MSG_HIGHMEM_TOO_SMALL \ + "only %luMB highmem pages available, ignoring highmem size of %luMB!\n" -pteval_t __supported_pte_mask __read_mostly = ~_PAGE_NX; -EXPORT_SYMBOL_GPL(__supported_pte_mask); +#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: + */ +static void __init highmem_pfn_init(void) +{ + max_low_pfn = MAXMEM_PFN; -#ifdef CONFIG_X86_PAE + if (highmem_pages == -1) + highmem_pages = max_pfn - MAXMEM_PFN; + + if (highmem_pages + MAXMEM_PFN < max_pfn) + max_pfn = MAXMEM_PFN + highmem_pages; -static int disable_nx __initdata; + 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 */ +} /* - * noexec = on|off - * - * Control non executable mappings. - * - * on Enable - * off Disable + * Determine low and high memory ranges: */ -static int __init noexec_setup(char *str) +void __init find_low_pfn_range(void) { - if (!str || !strcmp(str, "on")) { - if (cpu_has_nx) { - __supported_pte_mask |= _PAGE_NX; - disable_nx = 0; - } - } else { - if (!strcmp(str, "off")) { - disable_nx = 1; - __supported_pte_mask &= ~_PAGE_NX; - } else { - return -EINVAL; - } - } + /* it could update max_pfn */ - return 0; + if (max_pfn <= MAXMEM_PFN) + lowmem_pfn_init(); + else + highmem_pfn_init(); } -early_param("noexec", noexec_setup); -static void __init set_nx(void) +#ifndef CONFIG_NEED_MULTIPLE_NODES +void __init initmem_init(void) { - unsigned int v[4], l, h; +#ifdef CONFIG_HIGHMEM + highstart_pfn = highend_pfn = max_pfn; + if (max_pfn > max_low_pfn) + highstart_pfn = max_low_pfn; + printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", + pages_to_mb(highend_pfn - highstart_pfn)); + high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; +#else + high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; +#endif - if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) { - cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]); + memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0); + sparse_memory_present_with_active_regions(0); - if ((v[3] & (1 << 20)) && !disable_nx) { - rdmsr(MSR_EFER, l, h); - l |= EFER_NX; - wrmsr(MSR_EFER, l, h); - nx_enabled = 1; - __supported_pte_mask |= _PAGE_NX; - } - } -} +#ifdef CONFIG_FLATMEM + max_mapnr = IS_ENABLED(CONFIG_HIGHMEM) ? highend_pfn : max_low_pfn; #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 */ + +void __init setup_bootmem_allocator(void) +{ + printk(KERN_INFO " mapped low ram: 0 - %08lx\n", + max_pfn_mapped<<PAGE_SHIFT); + printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT); +} /* * paging_init() sets up the page tables - note that the first 8MB are @@ -531,25 +696,26 @@ static void __init set_nx(void) */ void __init paging_init(void) { -#ifdef CONFIG_X86_PAE - set_nx(); - if (nx_enabled) - printk(KERN_INFO "NX (Execute Disable) protection: active\n"); -#endif pagetable_init(); - load_cr3(swapper_pg_dir); - __flush_tlb_all(); kmap_init(); + + /* + * NOTE: at this point the bootmem allocator is fully available. + */ + olpc_dt_build_devicetree(); + sparse_memory_present_with_active_regions(MAX_NUMNODES); + sparse_init(); + zone_sizes_init(); } /* * Test if the WP bit works in supervisor mode. It isn't supported on 386's - * and also on some strange 486's (NexGen etc.). All 586+'s are OK. This - * used to involve black magic jumps to work around some nasty CPU bugs, - * but fortunately the switch to using exceptions got rid of all that. + * and also on some strange 486's. All 586+'s are OK. This used to involve + * black magic jumps to work around some nasty CPU bugs, but fortunately the + * switch to using exceptions got rid of all that. */ static void __init test_wp_bit(void) { @@ -557,77 +723,42 @@ static void __init test_wp_bit(void) "Checking if this processor honours the WP bit even in supervisor mode..."); /* Any page-aligned address will do, the test is non-destructive */ - __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY); + __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_KERNEL_RO); boot_cpu_data.wp_works_ok = do_test_wp_bit(); clear_fixmap(FIX_WP_TEST); if (!boot_cpu_data.wp_works_ok) { printk(KERN_CONT "No.\n"); -#ifdef CONFIG_X86_WP_WORKS_OK - panic( - "This kernel doesn't support CPU's with broken WP. Recompile it for a 386!"); -#endif + panic("Linux doesn't support CPUs with broken WP."); } else { printk(KERN_CONT "Ok.\n"); } } -static struct kcore_list kcore_mem, kcore_vmalloc; - void __init mem_init(void) { - int codesize, reservedpages, datasize, initsize; - int tmp, bad_ppro; + pci_iommu_alloc(); #ifdef CONFIG_FLATMEM BUG_ON(!mem_map); #endif - bad_ppro = ppro_with_ram_bug(); + /* + * With CONFIG_DEBUG_PAGEALLOC initialization of highmem pages has to + * be done before free_all_bootmem(). Memblock use free low memory for + * temporary data (see find_range_array()) and for this purpose can use + * pages that was already passed to the buddy allocator, hence marked as + * not accessible in the page tables when compiled with + * CONFIG_DEBUG_PAGEALLOC. Otherwise order of initialization is not + * important here. + */ + set_highmem_pages_init(); -#ifdef CONFIG_HIGHMEM - /* check that fixmap and pkmap do not overlap */ - if (PKMAP_BASE + LAST_PKMAP*PAGE_SIZE >= FIXADDR_START) { - printk(KERN_ERR - "fixmap and kmap areas overlap - this will crash\n"); - printk(KERN_ERR "pkstart: %lxh pkend: %lxh fixstart %lxh\n", - PKMAP_BASE, PKMAP_BASE + LAST_PKMAP*PAGE_SIZE, - FIXADDR_START); - BUG(); - } -#endif /* this will put all low memory onto the freelists */ - totalram_pages += free_all_bootmem(); + free_all_bootmem(); - reservedpages = 0; - for (tmp = 0; tmp < max_low_pfn; tmp++) - /* - * Only count reserved RAM pages: - */ - if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp))) - reservedpages++; - - set_highmem_pages_init(bad_ppro); - - codesize = (unsigned long) &_etext - (unsigned long) &_text; - datasize = (unsigned long) &_edata - (unsigned long) &_etext; - initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); - kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); - - printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, " - "%dk reserved, %dk data, %dk init, %ldk highmem)\n", - (unsigned long) nr_free_pages() << (PAGE_SHIFT-10), - num_physpages << (PAGE_SHIFT-10), - codesize >> 10, - reservedpages << (PAGE_SHIFT-10), - datasize >> 10, - initsize >> 10, - (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10)) - ); - -#if 1 /* double-sanity-check paranoia */ + after_bootmem = 1; + + mem_init_print_info(NULL); printk(KERN_INFO "virtual kernel memory layout:\n" " fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n" #ifdef CONFIG_HIGHMEM @@ -662,28 +793,32 @@ void __init mem_init(void) (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_RANDOMIZE_BASE + BUILD_BUG_ON(CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE); +#endif + #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(VMALLOC_START >= VMALLOC_END); BUG_ON((unsigned long)high_memory > VMALLOC_START); -#endif /* double-sanity-check paranoia */ if (boot_cpu_data.wp_works_ok < 0) test_wp_bit(); - - cpa_init(); - - /* - * Subtle. SMP is doing it's boot stuff late (because it has to - * fork idle threads) - but it also needs low mappings for the - * protected-mode entry to work. We zap these entries only after - * the WP-bit has been tested. - */ -#ifndef CONFIG_SMP - zap_low_mappings(); -#endif } #ifdef CONFIG_MEMORY_HOTPLUG @@ -694,9 +829,21 @@ int arch_add_memory(int nid, u64 start, u64 size) unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - return __add_pages(zone, start_pfn, nr_pages); + return __add_pages(nid, zone, start_pfn, nr_pages); +} + +#ifdef CONFIG_MEMORY_HOTREMOVE +int arch_remove_memory(u64 start, u64 size) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + + zone = page_zone(pfn_to_page(start_pfn)); + return __remove_pages(zone, start_pfn, nr_pages); } #endif +#endif /* * This function cannot be __init, since exceptions don't work in that @@ -726,6 +873,53 @@ static noinline int do_test_wp_bit(void) 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); @@ -735,6 +929,8 @@ void mark_rodata_ro(void) 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); @@ -743,6 +939,7 @@ void mark_rodata_ro(void) 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); @@ -757,51 +954,7 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); #endif + mark_nxdata_nx(); } #endif -void free_init_pages(char *what, unsigned long begin, unsigned long end) -{ -#ifdef CONFIG_DEBUG_PAGEALLOC - /* - * If debugging page accesses then do not free this memory but - * mark them not present - any buggy init-section access will - * create a kernel page fault: - */ - printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n", - begin, PAGE_ALIGN(end)); - set_memory_np(begin, (end - begin) >> PAGE_SHIFT); -#else - unsigned long addr; - - /* - * We just marked the kernel text read only above, now that - * we are going to free part of that, we need to make that - * writeable first. - */ - set_memory_rw(begin, (end - begin) >> PAGE_SHIFT); - - for (addr = begin; addr < end; addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - init_page_count(virt_to_page(addr)); - memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE); - free_page(addr); - totalram_pages++; - } - printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); -#endif -} - -void free_initmem(void) -{ - free_init_pages("unused kernel memory", - (unsigned long)(&__init_begin), - (unsigned long)(&__init_end)); -} - -#ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) -{ - free_init_pages("initrd memory", start, end); -} -#endif |