arch/x86/mm/init_32.c

/*
 *
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 */

#include <linux/module.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/swap.h>
#include <linux/smp.h>
#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/proc_fs.h>
#include <linux/memory_hotplug.h>
#include <linux/initrd.h>
#include <linux/cpumask.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>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/bugs.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
#include <asm/sections.h>
#include <asm/paravirt.h>
#include <asm/setup.h>
#include <asm/cacheflush.h>

unsigned long max_low_pfn_mapped;
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);


static unsigned long __initdata table_start;
static unsigned long __meminitdata table_end;
static unsigned long __meminitdata table_top;

static int __initdata after_init_bootmem;

int direct_gbpages;

static __init void *alloc_low_page(void)
{
	unsigned long pfn = table_end++;
	void *adr;

	if (pfn >= table_top)
		panic("alloc_low_page: ran out of memory");

	adr = __va(pfn * PAGE_SIZE);
	memset(adr, 0, PAGE_SIZE);
	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_init_bootmem)
			pmd_table = (pmd_t *)alloc_bootmem_low_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_init_bootmem) {
#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);
		} 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);
}

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) < table_start
		|| (__pa(pte) >> PAGE_SHIFT) >= table_end)) {
		pte_t *newpte;
		int i;

		BUG_ON(after_init_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 >= PAGE_OFFSET && 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:
 */
static void __init kernel_physical_mapping_init(unsigned long start_pfn,
						unsigned long end_pfn,
						int use_pse)
{
	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;

	/*
	 * 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 >= 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:
			 */
			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);

				addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE +
					PAGE_OFFSET + PAGE_SIZE-1;

				if (is_kernel_text(addr) ||
				    is_kernel_text(addr2))
					prot = PAGE_KERNEL_LARGE_EXEC;

				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;
				continue;
			}
			pte = one_page_table_init(pmd);

			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;

				pages_4k++;
				if (mapping_iter == 1)
					set_pte(pte, pfn_pte(pfn, init_prot));
				else
					set_pte(pte, pfn_pte(pfn, prot));
			}
		}
	}
	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);

		/*
		 * 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;
	}
}

pte_t *kmap_pte;
pgprot_t kmap_prot;

static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr)
{
	return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
			vaddr), vaddr), vaddr);
}

static void __init kmap_init(void)
{
	unsigned long kmap_vstart;

	/*
	 * Cache the first kmap pte:
	 */
	kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
	kmap_pte = kmap_get_fixmap_pte(kmap_vstart);

	kmap_prot = PAGE_KERNEL;
}

#ifdef CONFIG_HIGHMEM
static void __init permanent_kmaps_init(pgd_t *pgd_base)
{
	unsigned long vaddr;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	vaddr = PKMAP_BASE;
	page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base);

	pgd = swapper_pg_dir + pgd_index(vaddr);
	pud = pud_offset(pgd, vaddr);
	pmd = pmd_offset(pud, vaddr);
	pte = pte_offset_kernel(pmd, vaddr);
	pkmap_page_table = pte;
}

static void __init add_one_highpage_init(struct page *page, int pfn)
{
	ClearPageReserved(page);
	init_page_count(page);
	__free_page(page);
	totalhigh_pages++;
}

struct add_highpages_data {
	unsigned long start_pfn;
	unsigned long end_pfn;
};

static int __init add_highpages_work_fn(unsigned long start_pfn,
					 unsigned long end_pfn, void *datax)
{
	int node_pfn;
	struct page *page;
	unsigned long final_start_pfn, final_end_pfn;
	struct add_highpages_data *data;

	data = (struct add_highpages_data *)datax;

	final_start_pfn = max(start_pfn, data->start_pfn);
	final_end_pfn = min(end_pfn, data->end_pfn);
	if (final_start_pfn >= final_end_pfn)
		return 0;

	for (node_pfn = final_start_pfn; node_pfn < final_end_pfn;
	     node_pfn++) {
		if (!pfn_valid(node_pfn))
			continue;
		page = pfn_to_page(node_pfn);
		add_one_highpage_init(page, node_pfn);
	}

	return 0;

}

void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn,
					      unsigned long end_pfn)
{
	struct add_highpages_data data;

	data.start_pfn = start_pfn;
	data.end_pfn = end_pfn;

	work_with_active_regions(nid, add_highpages_work_fn, &data);
}

#else
static inline void permanent_kmaps_init(pgd_t *pgd_base)
{
}
#endif /* CONFIG_HIGHMEM */

void __init native_pagetable_setup_start(pgd_t *base)
{
	unsigned long pfn, va;
	pgd_t *pgd;
	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:
	 */
	for (pfn = max_low_pfn + 1; pfn < 1<<(32-PAGE_SHIFT); pfn++) {
		va = PAGE_OFFSET + (pfn<<PAGE_SHIFT);
		pgd = base + pgd_index(va);
		if (!pgd_present(*pgd))
			break;

		pud = pud_offset(pgd, va);
		pmd = pmd_offset(pud, va);
		if (!pmd_present(*pmd))
			break;

		pte = pte_offset_kernel(pmd, va);
		if (!pte_present(*pte))
			break;

		pte_clear(NULL, va, pte);
	}
	paravirt_alloc_pmd(&init_mm, __pa(base) >> 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.
 */
static 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);
}

#ifdef CONFIG_ACPI_SLEEP
/*
 * ACPI suspend needs this for resume, because things like the intel-agp
 * driver might have split up a kernel 4MB mapping.
 */
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)
{
}
#endif /* !CONFIG_ACPI_SLEEP */

void zap_low_mappings(void)
{
	int i;

	/*
	 * 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 < KERNEL_PGD_BOUNDARY; i++) {
#ifdef CONFIG_X86_PAE
		set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
#else
		set_pgd(swapper_pg_dir+i, __pgd(0));
#endif
	}
	flush_tlb_all();
}

int nx_enabled;

pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
EXPORT_SYMBOL_GPL(__supported_pte_mask);

#ifdef CONFIG_X86_PAE

static int disable_nx __initdata;

/*
 * noexec = on|off
 *
 * Control non executable mappings.
 *
 * on      Enable
 * off     Disable
 */
static int __init noexec_setup(char *str)
{
	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;
		}
	}

	return 0;
}
early_param("noexec", noexec_setup);

static void __init set_nx(void)
{
	unsigned int v[4], l, h;

	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);

		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;
		}
	}
}
#endif

/* 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(unsigned long start_pfn,
				  unsigned long end_pfn)
{
#ifdef CONFIG_HIGHMEM
	highstart_pfn = highend_pfn = max_pfn;
	if (max_pfn > max_low_pfn)
		highstart_pfn = max_low_pfn;
	memory_present(0, 0, highend_pfn);
	e820_register_active_regions(0, 0, highend_pfn);
	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
	memory_present(0, 0, max_low_pfn);
	e820_register_active_regions(0, 0, max_low_pfn);
	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
	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);
}

static unsigned long __init setup_node_bootmem(int nodeid,
				 unsigned long start_pfn,
				 unsigned long end_pfn,
				 unsigned long bootmap)
{
	unsigned long bootmap_size;

	if (start_pfn > max_low_pfn)
		return bootmap;
	if (end_pfn > max_low_pfn)
		end_pfn = max_low_pfn;

	/* don't touch min_low_pfn */
	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
					 bootmap >> PAGE_SHIFT,
					 start_pfn, end_pfn);
	printk(KERN_INFO "  node %d low ram: %08lx - %08lx\n",
		nodeid, start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
	printk(KERN_INFO "  node %d bootmap %08lx - %08lx\n",
		 nodeid, bootmap, bootmap + bootmap_size);
	free_bootmem_with_active_regions(nodeid, end_pfn);
	early_res_to_bootmem(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);

	return bootmap + bootmap_size;
}

void __init setup_bootmem_allocator(void)
{
	int nodeid;
	unsigned long bootmap_size, bootmap;
	/*
	 * Initialize the boot-time allocator (with low memory only):
	 */
	bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
	bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
				 PAGE_SIZE);
	if (bootmap == -1L)
		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");

	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);

#ifdef CONFIG_NEED_MULTIPLE_NODES
	for_each_online_node(nodeid)
		bootmap = setup_node_bootmem(nodeid, node_start_pfn[nodeid],
					node_end_pfn[nodeid], bootmap);
#else
	bootmap = setup_node_bootmem(0, 0, max_low_pfn, bootmap);
#endif

	after_init_bootmem = 1;
}

static void __init find_early_table_space(unsigned long end, int use_pse,
					  int use_gbpages)
{
	unsigned long puds, pmds, ptes, tables, start;

	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);

	if (use_gbpages) {
		unsigned long extra;

		extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
		pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
	} else
		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;

	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);

	if (use_pse) {
		unsigned long extra;

		extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
#ifdef CONFIG_X86_32
		extra += PMD_SIZE;
#endif
		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
	} else
		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;

	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);

#ifdef CONFIG_X86_32
	/* for fixmap */
	tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
#endif

	/*
	 * RED-PEN putting page tables only on node 0 could
	 * cause a hotspot and fill up ZONE_DMA. The page tables
	 * need roughly 0.5KB per GB.
	 */
#ifdef CONFIG_X86_32
	start = 0x7000;
	table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
					tables, PAGE_SIZE);
#else /* CONFIG_X86_64 */
	start = 0x8000;
	table_start = find_e820_area(start, end, tables, PAGE_SIZE);
#endif
	if (table_start == -1UL)
		panic("Cannot find space for the kernel page tables");

	table_start >>= PAGE_SHIFT;
	table_end = table_start;
	table_top = table_start + (tables >> PAGE_SHIFT);

	printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
		end, table_start << PAGE_SHIFT, table_top << PAGE_SHIFT);
}

struct map_range {
	unsigned long start;
	unsigned long end;
	unsigned page_size_mask;
};

#define NR_RANGE_MR 3

static int save_mr(struct map_range *mr, int nr_range,
		   unsigned long start_pfn, unsigned long end_pfn,
		   unsigned long page_size_mask)
{
	if (start_pfn < end_pfn) {
		if (nr_range >= NR_RANGE_MR)
			panic("run out of range for init_memory_mapping\n");
		mr[nr_range].start = start_pfn<<PAGE_SHIFT;
		mr[nr_range].end   = end_pfn<<PAGE_SHIFT;
		mr[nr_range].page_size_mask = page_size_mask;
		nr_range++;
	}

	return nr_range;
}

/*
 * Setup the direct mapping of the physical memory at PAGE_OFFSET.
 * This runs before bootmem is initialized and gets pages directly from
 * the physical memory. To access them they are temporarily mapped.
 */
unsigned long __init_refok init_memory_mapping(unsigned long start,
					       unsigned long end)
{
	unsigned long page_size_mask = 0;
	unsigned long start_pfn, end_pfn;
	unsigned long pos;

	struct map_range mr[NR_RANGE_MR];
	int nr_range, i;
	int use_pse, use_gbpages;

	printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);

#ifdef CONFIG_DEBUG_PAGEALLOC
	/*
	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
	 * This will simplify cpa(), which otherwise needs to support splitting
	 * large pages into small in interrupt context, etc.
	 */
	use_pse = use_gbpages = 0;
#else
	use_pse = cpu_has_pse;
	use_gbpages = direct_gbpages;
#endif

#ifdef CONFIG_X86_PAE
	set_nx();
	if (nx_enabled)
		printk(KERN_INFO "NX (Execute Disable) protection: active\n");
#endif

	/* 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);
		__supported_pte_mask |= _PAGE_GLOBAL;
	}

	if (use_gbpages)
		page_size_mask |= 1 << PG_LEVEL_1G;
	if (use_pse)
		page_size_mask |= 1 << PG_LEVEL_2M;

	memset(mr, 0, sizeof(mr));
	nr_range = 0;

	/*
	 * 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.
	 */
	/* head if not big page alignment ? */
	start_pfn = start >> PAGE_SHIFT;
	pos = start_pfn << PAGE_SHIFT;
	if (pos == 0)
		end_pfn = 1<<(PMD_SHIFT - PAGE_SHIFT);
	else
		end_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
				 << (PMD_SHIFT - PAGE_SHIFT);
	if (end_pfn > (end >> PAGE_SHIFT))
		end_pfn = end >> PAGE_SHIFT;
	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
		pos = end_pfn << PAGE_SHIFT;
	}

	/* big page (2M) range */
	start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
			 << (PMD_SHIFT - PAGE_SHIFT);
	end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
				page_size_mask & (1<<PG_LEVEL_2M));
		pos = end_pfn << PAGE_SHIFT;
	}

	/* tail is not big page (2M) alignment */
	start_pfn = pos>>PAGE_SHIFT;
	end_pfn = end>>PAGE_SHIFT;
	if (start_pfn < end_pfn)
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);

	/* try to merge same page size and continuous */
	for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
		unsigned long old_start;
		if (mr[i].end != mr[i+1].start ||
		    mr[i].page_size_mask != mr[i+1].page_size_mask)
			continue;
		/* move it */
		old_start = mr[i].start;
		memmove(&mr[i], &mr[i+1],
			(nr_range - 1 - i) * sizeof(struct map_range));
		mr[i--].start = old_start;
		nr_range--;
	}

	for (i = 0; i < nr_range; i++)
		printk(KERN_DEBUG " %010lx - %010lx page %s\n",
				mr[i].start, mr[i].end,
			(mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
			 (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));

	/*
	 * Find space for the kernel direct mapping tables.
	 *
	 * Later we should allocate these tables in the local node of the
	 * memory mapped. Unfortunately this is done currently before the
	 * nodes are discovered.
	 */
	if (!after_init_bootmem)
		find_early_table_space(end, use_pse, use_gbpages);

	for (i = 0; i < nr_range; i++)
		kernel_physical_mapping_init(
				mr[i].start >> PAGE_SHIFT,
				mr[i].end >> PAGE_SHIFT,
				mr[i].page_size_mask == (1<<PG_LEVEL_2M));

	early_ioremap_page_table_range_init();

	load_cr3(swapper_pg_dir);

	__flush_tlb_all();

	if (!after_init_bootmem)
		reserve_early(table_start << PAGE_SHIFT,
				 table_end << PAGE_SHIFT, "PGTABLE");

	if (!after_init_bootmem)
		early_memtest(start, end);

	return end >> PAGE_SHIFT;
}


/*
 * paging_init() sets up the page tables - note that the first 8MB are
 * already mapped by head.S.
 *
 * This routines also unmaps the page at virtual kernel address 0, so
 * that we can trap those pesky NULL-reference errors in the kernel.
 */
void __init paging_init(void)
{
	pagetable_init();

	__flush_tlb_all();

	kmap_init();

	/*
	 * NOTE: at this point the bootmem allocator is fully available.
	 */
	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. 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)
{
	printk(KERN_INFO
  "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);
	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
	} 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;

	pci_iommu_alloc();

#ifdef CONFIG_FLATMEM
	BUG_ON(!mem_map);
#endif
	/* this will put all low memory onto the freelists */
	totalram_pages += 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();

	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))
	       );

	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();

	save_pg_dir();
	zap_low_mappings();
}

#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);

void mark_rodata_ro(void)
{
	unsigned long start = PFN_ALIGN(_text);
	unsigned long size = PFN_ALIGN(_etext) - start;

#ifndef CONFIG_DYNAMIC_FTRACE
	/* Dynamic tracing modifies the kernel text section */
	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
	printk(KERN_INFO "Write protecting the kernel text: %luk\n",
		size >> 10);

#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
#endif /* CONFIG_DYNAMIC_FTRACE */

	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
}
#endif

int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
				   int flags)
{
	return reserve_bootmem(phys, len, flags);
}