init_64.c

/*
 *  linux/arch/x86_64/mm/init.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *  Copyright (C) 2000  Pavel Machek <pavel@suse.cz>
 *  Copyright (C) 2002,2003 Andi Kleen <ak@suse.de>
 */

#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/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/initrd.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/proc_fs.h>
#include <linux/pci.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>
#include <linux/memory_hotplug.h>
#include <linux/nmi.h>

#include <asm/processor.h>
#include <asm/bios_ebda.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/smp.h>
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/numa.h>
#include <asm/cacheflush.h>

/*
 * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
 * The direct mapping extends to max_pfn_mapped, so that we can directly access
 * apertures, ACPI and other tables without having to play with fixmaps.
 */
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;

static unsigned long dma_reserve __initdata;

DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);

int direct_gbpages
#ifdef CONFIG_DIRECT_GBPAGES
				= 1
#endif
;

static int __init parse_direct_gbpages_off(char *arg)
{
	direct_gbpages = 0;
	return 0;
}
early_param("nogbpages", parse_direct_gbpages_off);

static int __init parse_direct_gbpages_on(char *arg)
{
	direct_gbpages = 1;
	return 0;
}
early_param("gbpages", parse_direct_gbpages_on);

/*
 * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
 * physical space so we can cache the place of the first one and move
 * around without checking the pgd every time.
 */

int after_bootmem;

pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
EXPORT_SYMBOL_GPL(__supported_pte_mask);

static int do_not_nx __cpuinitdata;

/*
 * noexec=on|off
 * Control non-executable mappings for 64-bit processes.
 *
 * on	Enable (default)
 * off	Disable
 */
static int __init nonx_setup(char *str)
{
	if (!str)
		return -EINVAL;
	if (!strncmp(str, "on", 2)) {
		__supported_pte_mask |= _PAGE_NX;
		do_not_nx = 0;
	} else if (!strncmp(str, "off", 3)) {
		do_not_nx = 1;
		__supported_pte_mask &= ~_PAGE_NX;
	}
	return 0;
}
early_param("noexec", nonx_setup);

void __cpuinit check_efer(void)
{
	unsigned long efer;

	rdmsrl(MSR_EFER, efer);
	if (!(efer & EFER_NX) || do_not_nx)
		__supported_pte_mask &= ~_PAGE_NX;
}

int force_personality32;

/*
 * noexec32=on|off
 * Control non executable heap for 32bit processes.
 * To control the stack too use noexec=off
 *
 * on	PROT_READ does not imply PROT_EXEC for 32-bit processes (default)
 * off	PROT_READ implies PROT_EXEC
 */
static int __init nonx32_setup(char *str)
{
	if (!strcmp(str, "on"))
		force_personality32 &= ~READ_IMPLIES_EXEC;
	else if (!strcmp(str, "off"))
		force_personality32 |= READ_IMPLIES_EXEC;
	return 1;
}
__setup("noexec32=", nonx32_setup);

/*
 * NOTE: This function is marked __ref because it calls __init function
 * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
 */
static __ref void *spp_getpage(void)
{
	void *ptr;

	if (after_bootmem)
		ptr = (void *) get_zeroed_page(GFP_ATOMIC);
	else
		ptr = alloc_bootmem_pages(PAGE_SIZE);

	if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) {
		panic("set_pte_phys: cannot allocate page data %s\n",
			after_bootmem ? "after bootmem" : "");
	}

	pr_debug("spp_getpage %p\n", ptr);

	return ptr;
}

void
set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
{
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	pud = pud_page + pud_index(vaddr);
	if (pud_none(*pud)) {
		pmd = (pmd_t *) spp_getpage();
		pud_populate(&init_mm, pud, pmd);
		if (pmd != pmd_offset(pud, 0)) {
			printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
				pmd, pmd_offset(pud, 0));
			return;
		}
	}
	pmd = pmd_offset(pud, vaddr);
	if (pmd_none(*pmd)) {
		pte = (pte_t *) spp_getpage();
		pmd_populate_kernel(&init_mm, pmd, pte);
		if (pte != pte_offset_kernel(pmd, 0)) {
			printk(KERN_ERR "PAGETABLE BUG #02!\n");
			return;
		}
	}

	pte = pte_offset_kernel(pmd, vaddr);
	set_pte(pte, new_pte);

	/*
	 * It's enough to flush this one mapping.
	 * (PGE mappings get flushed as well)
	 */
	__flush_tlb_one(vaddr);
}

void
set_pte_vaddr(unsigned long vaddr, pte_t pteval)
{
	pgd_t *pgd;
	pud_t *pud_page;

	pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval));

	pgd = pgd_offset_k(vaddr);
	if (pgd_none(*pgd)) {
		printk(KERN_ERR
			"PGD FIXMAP MISSING, it should be setup in head.S!\n");
		return;
	}
	pud_page = (pud_t*)pgd_page_vaddr(*pgd);
	set_pte_vaddr_pud(pud_page, vaddr, pteval);
}

/*
 * Create large page table mappings for a range of physical addresses.
 */
static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
						pgprot_t prot)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;

	BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK));
	for (; size; phys += PMD_SIZE, size -= PMD_SIZE) {
		pgd = pgd_offset_k((unsigned long)__va(phys));
		if (pgd_none(*pgd)) {
			pud = (pud_t *) spp_getpage();
			set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE |
						_PAGE_USER));
		}
		pud = pud_offset(pgd, (unsigned long)__va(phys));
		if (pud_none(*pud)) {
			pmd = (pmd_t *) spp_getpage();
			set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE |
						_PAGE_USER));
		}
		pmd = pmd_offset(pud, phys);
		BUG_ON(!pmd_none(*pmd));
		set_pmd(pmd, __pmd(phys | pgprot_val(prot)));
	}
}

void __init init_extra_mapping_wb(unsigned long phys, unsigned long size)
{
	__init_extra_mapping(phys, size, PAGE_KERNEL_LARGE);
}

void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
{
	__init_extra_mapping(phys, size, PAGE_KERNEL_LARGE_NOCACHE);
}

/*
 * The head.S code sets up the kernel high mapping:
 *
 *   from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text)
 *
 * phys_addr holds the negative offset to the kernel, which is added
 * to the compile time generated pmds. This results in invalid pmds up
 * to the point where we hit the physaddr 0 mapping.
 *
 * We limit the mappings to the region from _text to _end.  _end is
 * rounded up to the 2MB boundary. This catches the invalid pmds as
 * well, as they are located before _text:
 */
void __init cleanup_highmap(void)
{
	unsigned long vaddr = __START_KERNEL_map;
	unsigned long end = roundup((unsigned long)_end, PMD_SIZE) - 1;
	pmd_t *pmd = level2_kernel_pgt;
	pmd_t *last_pmd = pmd + PTRS_PER_PMD;

	for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
		if (pmd_none(*pmd))
			continue;
		if (vaddr < (unsigned long) _text || vaddr > end)
			set_pmd(pmd, __pmd(0));
	}
}

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

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

	if (after_bootmem) {
		adr = (void *)get_zeroed_page(GFP_ATOMIC);
		*phys = __pa(adr);

		return adr;
	}

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

	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
	memset(adr, 0, PAGE_SIZE);
	*phys  = pfn * PAGE_SIZE;
	return adr;
}

static __ref void unmap_low_page(void *adr)
{
	if (after_bootmem)
		return;

	early_iounmap(adr, PAGE_SIZE);
}

static unsigned long __meminit
phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
	      pgprot_t prot)
{
	unsigned pages = 0;
	unsigned long last_map_addr = end;
	int i;

	pte_t *pte = pte_page + pte_index(addr);

	for(i = pte_index(addr); i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) {

		if (addr >= end) {
			if (!after_bootmem) {
				for(; i < PTRS_PER_PTE; i++, pte++)
					set_pte(pte, __pte(0));
			}
			break;
		}

		/*
		 * We will re-use the existing mapping.
		 * Xen for example has some special requirements, like mapping
		 * pagetable pages as RO. So assume someone who pre-setup
		 * these mappings are more intelligent.
		 */
		if (pte_val(*pte)) {
			pages++;
			continue;
		}

		if (0)
			printk("   pte=%p addr=%lx pte=%016lx\n",
			       pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte);
		pages++;
		set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, prot));
		last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE;
	}

	update_page_count(PG_LEVEL_4K, pages);

	return last_map_addr;
}

static unsigned long __meminit
phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end,
		pgprot_t prot)
{
	pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);

	return phys_pte_init(pte, address, end, prot);
}

static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
	      unsigned long page_size_mask, pgprot_t prot)
{
	unsigned long pages = 0;
	unsigned long last_map_addr = end;

	int i = pmd_index(address);

	for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
		unsigned long pte_phys;
		pmd_t *pmd = pmd_page + pmd_index(address);
		pte_t *pte;
		pgprot_t new_prot = prot;

		if (address >= end) {
			if (!after_bootmem) {
				for (; i < PTRS_PER_PMD; i++, pmd++)
					set_pmd(pmd, __pmd(0));
			}
			break;
		}

		if (pmd_val(*pmd)) {
			if (!pmd_large(*pmd)) {
				spin_lock(&init_mm.page_table_lock);
				last_map_addr = phys_pte_update(pmd, address,
								end, prot);
				spin_unlock(&init_mm.page_table_lock);
				continue;
			}
			/*
			 * If we are ok with PG_LEVEL_2M mapping, then we will
			 * use the existing mapping,
			 *
			 * Otherwise, we will split the large page mapping but
			 * use the same existing protection bits except for
			 * large page, so that we don't violate Intel's TLB
			 * Application note (317080) which says, while changing
			 * the page sizes, new and old translations should
			 * not differ with respect to page frame and
			 * attributes.
			 */
			if (page_size_mask & (1 << PG_LEVEL_2M)) {
				pages++;
				continue;
			}
			new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
		}

		if (page_size_mask & (1<<PG_LEVEL_2M)) {
			pages++;
			spin_lock(&init_mm.page_table_lock);
			set_pte((pte_t *)pmd,
				pfn_pte(address >> PAGE_SHIFT,
					__pgprot(pgprot_val(prot) | _PAGE_PSE)));
			spin_unlock(&init_mm.page_table_lock);
			last_map_addr = (address & PMD_MASK) + PMD_SIZE;
			continue;
		}

		pte = alloc_low_page(&pte_phys);
		last_map_addr = phys_pte_init(pte, address, end, new_prot);
		unmap_low_page(pte);

		spin_lock(&init_mm.page_table_lock);
		pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
		spin_unlock(&init_mm.page_table_lock);
	}
	update_page_count(PG_LEVEL_2M, pages);
	return last_map_addr;
}

static unsigned long __meminit
phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
		unsigned long page_size_mask, pgprot_t prot)
{
	pmd_t *pmd = pmd_offset(pud, 0);
	unsigned long last_map_addr;

	last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask, prot);
	__flush_tlb_all();
	return last_map_addr;
}

static unsigned long __meminit
phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
			 unsigned long page_size_mask)
{
	unsigned long pages = 0;
	unsigned long last_map_addr = end;
	int i = pud_index(addr);

	for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE) {
		unsigned long pmd_phys;
		pud_t *pud = pud_page + pud_index(addr);
		pmd_t *pmd;
		pgprot_t prot = PAGE_KERNEL;

		if (addr >= end)
			break;

		if (!after_bootmem &&
				!e820_any_mapped(addr, addr+PUD_SIZE, 0)) {
			set_pud(pud, __pud(0));
			continue;
		}

		if (pud_val(*pud)) {
			if (!pud_large(*pud)) {
				last_map_addr = phys_pmd_update(pud, addr, end,
							 page_size_mask, prot);
				continue;
			}
			/*
			 * If we are ok with PG_LEVEL_1G mapping, then we will
			 * use the existing mapping.
			 *
			 * Otherwise, we will split the gbpage mapping but use
			 * the same existing protection  bits except for large
			 * page, so that we don't violate Intel's TLB
			 * Application note (317080) which says, while changing
			 * the page sizes, new and old translations should
			 * not differ with respect to page frame and
			 * attributes.
			 */
			if (page_size_mask & (1 << PG_LEVEL_1G)) {
				pages++;
				continue;
			}
			prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
		}

		if (page_size_mask & (1<<PG_LEVEL_1G)) {
			pages++;
			spin_lock(&init_mm.page_table_lock);
			set_pte((pte_t *)pud,
				pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
			spin_unlock(&init_mm.page_table_lock);
			last_map_addr = (addr & PUD_MASK) + PUD_SIZE;
			continue;
		}

		pmd = alloc_low_page(&pmd_phys);
		last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
					      prot);
		unmap_low_page(pmd);

		spin_lock(&init_mm.page_table_lock);
		pud_populate(&init_mm, pud, __va(pmd_phys));
		spin_unlock(&init_mm.page_table_lock);
	}
	__flush_tlb_all();

	update_page_count(PG_LEVEL_1G, pages);

	return last_map_addr;
}

static unsigned long __meminit
phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end,
		 unsigned long page_size_mask)
{
	pud_t *pud;

	pud = (pud_t *)pgd_page_vaddr(*pgd);

	return phys_pud_init(pud, addr, end, page_size_mask);
}

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);
		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
	} else
		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);

	/*
	 * 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.
	 */
	start = 0x8000;
	table_start = find_e820_area(start, end, tables, PAGE_SIZE);
	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);
}

static void __init init_gbpages(void)
{
	if (direct_gbpages && cpu_has_gbpages)
		printk(KERN_INFO "Using GB pages for direct mapping\n");
	else
		direct_gbpages = 0;
}

static unsigned long __meminit kernel_physical_mapping_init(unsigned long start,
						unsigned long end,
						unsigned long page_size_mask)
{

	unsigned long next, last_map_addr = end;

	start = (unsigned long)__va(start);
	end = (unsigned long)__va(end);

	for (; start < end; start = next) {
		pgd_t *pgd = pgd_offset_k(start);
		unsigned long pud_phys;
		pud_t *pud;

		next = (start + PGDIR_SIZE) & PGDIR_MASK;
		if (next > end)
			next = end;

		if (pgd_val(*pgd)) {
			last_map_addr = phys_pud_update(pgd, __pa(start),
						 __pa(end), page_size_mask);
			continue;
		}

		pud = alloc_low_page(&pud_phys);
		last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
						 page_size_mask);
		unmap_low_page(pud);

		spin_lock(&init_mm.page_table_lock);
		pgd_populate(&init_mm, pgd, __va(pud_phys));
		spin_unlock(&init_mm.page_table_lock);
	}
	__flush_tlb_all();

	return last_map_addr;
}

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

#define NR_RANGE_MR 5

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 last_map_addr = 0;
	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);

	/*
	 * 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_bootmem)
		init_gbpages();

#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

	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;

	/* head if not big page alignment ?*/
	start_pfn = start >> PAGE_SHIFT;
	pos = start_pfn << PAGE_SHIFT;
	end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
			<< (PMD_SHIFT - 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 = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
			 << (PUD_SHIFT - PAGE_SHIFT);
	if (end_pfn > ((end>>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;
	}

	/* big page (1G) range */
	start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
			 << (PUD_SHIFT - PAGE_SHIFT);
	end_pfn = (end >> PUD_SHIFT) << (PUD_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)|(1<<PG_LEVEL_1G)));
		pos = end_pfn << PAGE_SHIFT;
	}

	/* tail is not big page (1G) alignment */
	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;
	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"));

	if (!after_bootmem)
		find_early_table_space(end, use_pse, use_gbpages);

	for (i = 0; i < nr_range; i++)
		last_map_addr = kernel_physical_mapping_init(
					mr[i].start, mr[i].end,
					mr[i].page_size_mask);

	if (!after_bootmem)
		mmu_cr4_features = read_cr4();
	__flush_tlb_all();

	if (!after_bootmem && table_end > table_start)
		reserve_early(table_start << PAGE_SHIFT,
				 table_end << PAGE_SHIFT, "PGTABLE");

	printk(KERN_INFO "last_map_addr: %lx end: %lx\n",
			 last_map_addr, end);

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

	return last_map_addr >> PAGE_SHIFT;
}

#ifndef CONFIG_NUMA
void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long bootmap_size, bootmap;

	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
	bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size,
				 PAGE_SIZE);
	if (bootmap == -1L)
		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
	/* don't touch min_low_pfn */
	bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
					 0, end_pfn);
	e820_register_active_regions(0, start_pfn, end_pfn);
	free_bootmem_with_active_regions(0, end_pfn);
	early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
	reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
}

void __init paging_init(void)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES];

	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
	max_zone_pfns[ZONE_NORMAL] = max_pfn;

	memory_present(0, 0, max_pfn);
	sparse_init();
	free_area_init_nodes(max_zone_pfns);
}
#endif

/*
 * Memory hotplug specific functions
 */
#ifdef CONFIG_MEMORY_HOTPLUG
/*
 * Memory is added always to NORMAL zone. This means you will never get
 * additional DMA/DMA32 memory.
 */
int arch_add_memory(int nid, u64 start, u64 size)
{
	struct pglist_data *pgdat = NODE_DATA(nid);
	struct zone *zone = pgdat->node_zones + ZONE_NORMAL;
	unsigned long last_mapped_pfn, start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;
	int ret;

	last_mapped_pfn = init_memory_mapping(start, start + size);
	if (last_mapped_pfn > max_pfn_mapped)
		max_pfn_mapped = last_mapped_pfn;

	ret = __add_pages(nid, zone, start_pfn, nr_pages);
	WARN_ON_ONCE(ret);

	return ret;
}
EXPORT_SYMBOL_GPL(arch_add_memory);

#if !defined(CONFIG_ACPI_NUMA) && defined(CONFIG_NUMA)
int memory_add_physaddr_to_nid(u64 start)
{
	return 0;
}
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif

#endif /* CONFIG_MEMORY_HOTPLUG */

/*
 * devmem_is_allowed() checks to see if /dev/mem access to a certain address
 * is valid. The argument is a physical page number.
 *
 *
 * On x86, access has to be given to the first megabyte of ram because that area
 * contains bios code and data regions used by X and dosemu and similar apps.
 * Access has to be given to non-kernel-ram areas as well, these contain the PCI
 * mmio resources as well as potential bios/acpi data regions.
 */
int devmem_is_allowed(unsigned long pagenr)
{
	if (pagenr <= 256)
		return 1;
	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
		return 0;
	if (!page_is_ram(pagenr))
		return 1;
	return 0;
}


static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
			 kcore_modules, kcore_vsyscall;

void __init mem_init(void)
{
	long codesize, reservedpages, datasize, initsize;
	unsigned long absent_pages;

	pci_iommu_alloc();

	/* clear_bss() already clear the empty_zero_page */

	reservedpages = 0;

	/* this will put all low memory onto the freelists */
#ifdef CONFIG_NUMA
	totalram_pages = numa_free_all_bootmem();
#else
	totalram_pages = free_all_bootmem();
#endif

	absent_pages = absent_pages_in_range(0, max_pfn);
	reservedpages = max_pfn - totalram_pages - absent_pages;
	after_bootmem = 1;

	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;

	/* Register memory areas for /proc/kcore */
	kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
		   VMALLOC_END-VMALLOC_START);
	kclist_add(&kcore_kernel, &_stext, _end - _stext);
	kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN);
	kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
				 VSYSCALL_END - VSYSCALL_START);

	printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
			 "%ldk absent, %ldk reserved, %ldk data, %ldk init)\n",
		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
		max_pfn << (PAGE_SHIFT-10),
		codesize >> 10,
		absent_pages << (PAGE_SHIFT-10),
		reservedpages << (PAGE_SHIFT-10),
		datasize >> 10,
		initsize >> 10);
}

void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
	unsigned long addr = begin;

	if (addr >= end)
		return;

	/*
	 * 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:
	 */
#ifdef CONFIG_DEBUG_PAGEALLOC
	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
		begin, PAGE_ALIGN(end));
	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
#else
	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);

	for (; addr < end; addr += PAGE_SIZE) {
		ClearPageReserved(virt_to_page(addr));
		init_page_count(virt_to_page(addr));
		memset((void *)(addr & ~(PAGE_SIZE-1)),
			POISON_FREE_INITMEM, PAGE_SIZE);
		free_page(addr);
		totalram_pages++;
	}
#endif
}

void free_initmem(void)
{
	free_init_pages("unused kernel memory",
			(unsigned long)(&__init_begin),
			(unsigned long)(&__init_end));
}

#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(_stext), end = PFN_ALIGN(__end_rodata);
	unsigned long rodata_start =
		((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;

#ifdef CONFIG_DYNAMIC_FTRACE
	/* Dynamic tracing modifies the kernel text section */
	start = rodata_start;
#endif

	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",