memory.c

/*
 *  linux/mm/memory.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 */

/*
 * demand-loading started 01.12.91 - seems it is high on the list of
 * things wanted, and it should be easy to implement. - Linus
 */

/*
 * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
 * pages started 02.12.91, seems to work. - Linus.
 *
 * Tested sharing by executing about 30 /bin/sh: under the old kernel it
 * would have taken more than the 6M I have free, but it worked well as
 * far as I could see.
 *
 * Also corrected some "invalidate()"s - I wasn't doing enough of them.
 */

/*
 * Real VM (paging to/from disk) started 18.12.91. Much more work and
 * thought has to go into this. Oh, well..
 * 19.12.91  -  works, somewhat. Sometimes I get faults, don't know why.
 *		Found it. Everything seems to work now.
 * 20.12.91  -  Ok, making the swap-device changeable like the root.
 */

/*
 * 05.04.94  -  Multi-page memory management added for v1.1.
 * 		Idea by Alex Bligh (alex@cconcepts.co.uk)
 *
 * 16.07.99  -  Support of BIGMEM added by Gerhard Wichert, Siemens AG
 *		(Gerhard.Wichert@pdb.siemens.de)
 *
 * Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
 */

#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/init.h>

#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>

#include <linux/swapops.h>
#include <linux/elf.h>

#ifndef CONFIG_NEED_MULTIPLE_NODES
/* use the per-pgdat data instead for discontigmem - mbligh */
unsigned long max_mapnr;
struct page *mem_map;

EXPORT_SYMBOL(max_mapnr);
EXPORT_SYMBOL(mem_map);
#endif

unsigned long num_physpages;
/*
 * A number of key systems in x86 including ioremap() rely on the assumption
 * that high_memory defines the upper bound on direct map memory, then end
 * of ZONE_NORMAL.  Under CONFIG_DISCONTIG this means that max_low_pfn and
 * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
 * and ZONE_HIGHMEM.
 */
void * high_memory;
unsigned long vmalloc_earlyreserve;

EXPORT_SYMBOL(num_physpages);
EXPORT_SYMBOL(high_memory);
EXPORT_SYMBOL(vmalloc_earlyreserve);

/*
 * If a p?d_bad entry is found while walking page tables, report
 * the error, before resetting entry to p?d_none.  Usually (but
 * very seldom) called out from the p?d_none_or_clear_bad macros.
 */

void pgd_clear_bad(pgd_t *pgd)
{
	pgd_ERROR(*pgd);
	pgd_clear(pgd);
}

void pud_clear_bad(pud_t *pud)
{
	pud_ERROR(*pud);
	pud_clear(pud);
}

void pmd_clear_bad(pmd_t *pmd)
{
	pmd_ERROR(*pmd);
	pmd_clear(pmd);
}

/*
 * Note: this doesn't free the actual pages themselves. That
 * has been handled earlier when unmapping all the memory regions.
 */
static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
{
	struct page *page = pmd_page(*pmd);
	pmd_clear(pmd);
	pte_free_tlb(tlb, page);
	dec_page_state(nr_page_table_pages);
	tlb->mm->nr_ptes--;
}

static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
				unsigned long addr, unsigned long end,
				unsigned long floor, unsigned long ceiling)
{
	pmd_t *pmd;
	unsigned long next;
	unsigned long start;

	start = addr;
	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		free_pte_range(tlb, pmd);
	} while (pmd++, addr = next, addr != end);

	start &= PUD_MASK;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= PUD_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		return;

	pmd = pmd_offset(pud, start);
	pud_clear(pud);
	pmd_free_tlb(tlb, pmd);
}

static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
				unsigned long addr, unsigned long end,
				unsigned long floor, unsigned long ceiling)
{
	pud_t *pud;
	unsigned long next;
	unsigned long start;

	start = addr;
	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		free_pmd_range(tlb, pud, addr, next, floor, ceiling);
	} while (pud++, addr = next, addr != end);

	start &= PGDIR_MASK;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= PGDIR_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		return;

	pud = pud_offset(pgd, start);
	pgd_clear(pgd);
	pud_free_tlb(tlb, pud);
}

/*
 * This function frees user-level page tables of a process.
 *
 * Must be called with pagetable lock held.
 */
void free_pgd_range(struct mmu_gather **tlb,
			unsigned long addr, unsigned long end,
			unsigned long floor, unsigned long ceiling)
{
	pgd_t *pgd;
	unsigned long next;
	unsigned long start;

	/*
	 * The next few lines have given us lots of grief...
	 *
	 * Why are we testing PMD* at this top level?  Because often
	 * there will be no work to do at all, and we'd prefer not to
	 * go all the way down to the bottom just to discover that.
	 *
	 * Why all these "- 1"s?  Because 0 represents both the bottom
	 * of the address space and the top of it (using -1 for the
	 * top wouldn't help much: the masks would do the wrong thing).
	 * The rule is that addr 0 and floor 0 refer to the bottom of
	 * the address space, but end 0 and ceiling 0 refer to the top
	 * Comparisons need to use "end - 1" and "ceiling - 1" (though
	 * that end 0 case should be mythical).
	 *
	 * Wherever addr is brought up or ceiling brought down, we must
	 * be careful to reject "the opposite 0" before it confuses the
	 * subsequent tests.  But what about where end is brought down
	 * by PMD_SIZE below? no, end can't go down to 0 there.
	 *
	 * Whereas we round start (addr) and ceiling down, by different
	 * masks at different levels, in order to test whether a table
	 * now has no other vmas using it, so can be freed, we don't
	 * bother to round floor or end up - the tests don't need that.
	 */

	addr &= PMD_MASK;
	if (addr < floor) {
		addr += PMD_SIZE;
		if (!addr)
			return;
	}
	if (ceiling) {
		ceiling &= PMD_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		end -= PMD_SIZE;
	if (addr > end - 1)
		return;

	start = addr;
	pgd = pgd_offset((*tlb)->mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		free_pud_range(*tlb, pgd, addr, next, floor, ceiling);
	} while (pgd++, addr = next, addr != end);

	if (!tlb_is_full_mm(*tlb))
		flush_tlb_pgtables((*tlb)->mm, start, end);
}

void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
		unsigned long floor, unsigned long ceiling)
{
	while (vma) {
		struct vm_area_struct *next = vma->vm_next;
		unsigned long addr = vma->vm_start;

		if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) {
			hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
				floor, next? next->vm_start: ceiling);
		} else {
			/*
			 * Optimization: gather nearby vmas into one call down
			 */
			while (next && next->vm_start <= vma->vm_end + PMD_SIZE
			  && !is_hugepage_only_range(vma->vm_mm, next->vm_start,
							HPAGE_SIZE)) {
				vma = next;
				next = vma->vm_next;
			}
			free_pgd_range(tlb, addr, vma->vm_end,
				floor, next? next->vm_start: ceiling);
		}
		vma = next;
	}
}

pte_t fastcall *pte_alloc_map(struct mm_struct *mm, pmd_t *pmd,
				unsigned long address)
{
	if (!pmd_present(*pmd)) {
		struct page *new;

		spin_unlock(&mm->page_table_lock);
		new = pte_alloc_one(mm, address);
		spin_lock(&mm->page_table_lock);
		if (!new)
			return NULL;
		/*
		 * Because we dropped the lock, we should re-check the
		 * entry, as somebody else could have populated it..
		 */
		if (pmd_present(*pmd)) {
			pte_free(new);
			goto out;
		}
		mm->nr_ptes++;
		inc_page_state(nr_page_table_pages);
		pmd_populate(mm, pmd, new);
	}
out:
	return pte_offset_map(pmd, address);
}

pte_t fastcall * pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
{
	if (!pmd_present(*pmd)) {
		pte_t *new;

		spin_unlock(&mm->page_table_lock);
		new = pte_alloc_one_kernel(mm, address);
		spin_lock(&mm->page_table_lock);
		if (!new)
			return NULL;

		/*
		 * Because we dropped the lock, we should re-check the
		 * entry, as somebody else could have populated it..
		 */
		if (pmd_present(*pmd)) {
			pte_free_kernel(new);
			goto out;
		}
		pmd_populate_kernel(mm, pmd, new);
	}
out:
	return pte_offset_kernel(pmd, address);
}

/*
 * copy one vm_area from one task to the other. Assumes the page tables
 * already present in the new task to be cleared in the whole range
 * covered by this vma.
 *
 * dst->page_table_lock is held on entry and exit,
 * but may be dropped within p[mg]d_alloc() and pte_alloc_map().
 */

static inline void
copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pte_t *dst_pte, pte_t *src_pte, unsigned long vm_flags,
		unsigned long addr)
{
	pte_t pte = *src_pte;
	struct page *page;
	unsigned long pfn;

	/* pte contains position in swap or file, so copy. */
	if (unlikely(!pte_present(pte))) {
		if (!pte_file(pte)) {
			swap_duplicate(pte_to_swp_entry(pte));
			/* make sure dst_mm is on swapoff's mmlist. */
			if (unlikely(list_empty(&dst_mm->mmlist))) {
				spin_lock(&mmlist_lock);
				list_add(&dst_mm->mmlist, &src_mm->mmlist);
				spin_unlock(&mmlist_lock);
			}
		}
		set_pte_at(dst_mm, addr, dst_pte, pte);
		return;
	}

	pfn = pte_pfn(pte);
	/* the pte points outside of valid memory, the
	 * mapping is assumed to be good, meaningful
	 * and not mapped via rmap - duplicate the
	 * mapping as is.
	 */
	page = NULL;
	if (pfn_valid(pfn))
		page = pfn_to_page(pfn);

	if (!page || PageReserved(page)) {
		set_pte_at(dst_mm, addr, dst_pte, pte);
		return;
	}

	/*
	 * If it's a COW mapping, write protect it both
	 * in the parent and the child
	 */
	if ((vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) {
		ptep_set_wrprotect(src_mm, addr, src_pte);
		pte = *src_pte;
	}

	/*
	 * If it's a shared mapping, mark it clean in
	 * the child
	 */
	if (vm_flags & VM_SHARED)
		pte = pte_mkclean(pte);
	pte = pte_mkold(pte);
	get_page(page);
	inc_mm_counter(dst_mm, rss);
	if (PageAnon(page))
		inc_mm_counter(dst_mm, anon_rss);
	set_pte_at(dst_mm, addr, dst_pte, pte);
	page_dup_rmap(page);
}

static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
		unsigned long addr, unsigned long end)
{
	pte_t *src_pte, *dst_pte;
	unsigned long vm_flags = vma->vm_flags;
	int progress;

again:
	dst_pte = pte_alloc_map(dst_mm, dst_pmd, addr);
	if (!dst_pte)
		return -ENOMEM;
	src_pte = pte_offset_map_nested(src_pmd, addr);

	progress = 0;
	spin_lock(&src_mm->page_table_lock);
	do {
		/*
		 * We are holding two locks at this point - either of them
		 * could generate latencies in another task on another CPU.
		 */
		if (progress >= 32 && (need_resched() ||
		    need_lockbreak(&src_mm->page_table_lock) ||
		    need_lockbreak(&dst_mm->page_table_lock)))
			break;
		if (pte_none(*src_pte)) {
			progress++;
			continue;
		}
		copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vm_flags, addr);
		progress += 8;
	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
	spin_unlock(&src_mm->page_table_lock);

	pte_unmap_nested(src_pte - 1);
	pte_unmap(dst_pte - 1);
	cond_resched_lock(&dst_mm->page_table_lock);
	if (addr != end)
		goto again;
	return 0;
}

static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
		unsigned long addr, unsigned long end)
{
	pmd_t *src_pmd, *dst_pmd;
	unsigned long next;

	dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
	if (!dst_pmd)
		return -ENOMEM;
	src_pmd = pmd_offset(src_pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(src_pmd))
			continue;
		if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
						vma, addr, next))
			return -ENOMEM;
	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
	return 0;
}

static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
		unsigned long addr, unsigned long end)
{
	pud_t *src_pud, *dst_pud;
	unsigned long next;

	dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
	if (!dst_pud)
		return -ENOMEM;
	src_pud = pud_offset(src_pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(src_pud))
			continue;
		if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
						vma, addr, next))
			return -ENOMEM;
	} while (dst_pud++, src_pud++, addr = next, addr != end);
	return 0;
}

int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		struct vm_area_struct *vma)
{
	pgd_t *src_pgd, *dst_pgd;
	unsigned long next;
	unsigned long addr = vma->vm_start;
	unsigned long end = vma->vm_end;

	if (is_vm_hugetlb_page(vma))
		return copy_hugetlb_page_range(dst_mm, src_mm, vma);

	dst_pgd = pgd_offset(dst_mm, addr);
	src_pgd = pgd_offset(src_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(src_pgd))
			continue;
		if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
						vma, addr, next))
			return -ENOMEM;
	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
	return 0;
}

static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	pte_t *pte;

	pte = pte_offset_map(pmd, addr);
	do {
		pte_t ptent = *pte;
		if (pte_none(ptent))
			continue;
		if (pte_present(ptent)) {
			struct page *page = NULL;
			unsigned long pfn = pte_pfn(ptent);
			if (pfn_valid(pfn)) {
				page = pfn_to_page(pfn);
				if (PageReserved(page))
					page = NULL;
			}
			if (unlikely(details) && page) {
				/*
				 * unmap_shared_mapping_pages() wants to
				 * invalidate cache without truncating:
				 * unmap shared but keep private pages.
				 */
				if (details->check_mapping &&
				    details->check_mapping != page->mapping)
					continue;
				/*
				 * Each page->index must be checked when
				 * invalidating or truncating nonlinear.
				 */
				if (details->nonlinear_vma &&
				    (page->index < details->first_index ||
				     page->index > details->last_index))
					continue;
			}
			ptent = ptep_get_and_clear(tlb->mm, addr, pte);
			tlb_remove_tlb_entry(tlb, pte, addr);
			if (unlikely(!page))
				continue;
			if (unlikely(details) && details->nonlinear_vma
			    && linear_page_index(details->nonlinear_vma,
						addr) != page->index)
				set_pte_at(tlb->mm, addr, pte,
					   pgoff_to_pte(page->index));
			if (pte_dirty(ptent))
				set_page_dirty(page);
			if (PageAnon(page))
				dec_mm_counter(tlb->mm, anon_rss);
			else if (pte_young(ptent))
				mark_page_accessed(page);
			tlb->freed++;
			page_remove_rmap(page);
			tlb_remove_page(tlb, page);
			continue;
		}
		/*
		 * If details->check_mapping, we leave swap entries;
		 * if details->nonlinear_vma, we leave file entries.
		 */
		if (unlikely(details))
			continue;
		if (!pte_file(ptent))
			free_swap_and_cache(pte_to_swp_entry(ptent));
		pte_clear(tlb->mm, addr, pte);
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap(pte - 1);
}

static inline void zap_pmd_range(struct mmu_gather *tlb, pud_t *pud,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		zap_pte_range(tlb, pmd, addr, next, details);
	} while (pmd++, addr = next, addr != end);
}

static inline void zap_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		zap_pmd_range(tlb, pud, addr, next, details);
	} while (pud++, addr = next, addr != end);
}

static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	pgd_t *pgd;
	unsigned long next;

	if (details && !details->check_mapping && !details->nonlinear_vma)
		details = NULL;

	BUG_ON(addr >= end);
	tlb_start_vma(tlb, vma);
	pgd = pgd_offset(vma->vm_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		zap_pud_range(tlb, pgd, addr, next, details);
	} while (pgd++, addr = next, addr != end);
	tlb_end_vma(tlb, vma);
}

#ifdef CONFIG_PREEMPT
# define ZAP_BLOCK_SIZE	(8 * PAGE_SIZE)
#else
/* No preempt: go for improved straight-line efficiency */
# define ZAP_BLOCK_SIZE	(1024 * PAGE_SIZE)
#endif

/**
 * unmap_vmas - unmap a range of memory covered by a list of vma's
 * @tlbp: address of the caller's struct mmu_gather
 * @mm: the controlling mm_struct
 * @vma: the starting vma
 * @start_addr: virtual address at which to start unmapping
 * @end_addr: virtual address at which to end unmapping
 * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here
 * @details: details of nonlinear truncation or shared cache invalidation
 *
 * Returns the end address of the unmapping (restart addr if interrupted).
 *
 * Unmap all pages in the vma list.  Called under page_table_lock.
 *
 * We aim to not hold page_table_lock for too long (for scheduling latency
 * reasons).  So zap pages in ZAP_BLOCK_SIZE bytecounts.  This means we need to
 * return the ending mmu_gather to the caller.
 *
 * Only addresses between `start' and `end' will be unmapped.
 *
 * The VMA list must be sorted in ascending virtual address order.
 *
 * unmap_vmas() assumes that the caller will flush the whole unmapped address
 * range after unmap_vmas() returns.  So the only responsibility here is to
 * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
 * drops the lock and schedules.
 */
unsigned long unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm,
		struct vm_area_struct *vma, unsigned long start_addr,
		unsigned long end_addr, unsigned long *nr_accounted,
		struct zap_details *details)
{
	unsigned long zap_bytes = ZAP_BLOCK_SIZE;
	unsigned long tlb_start = 0;	/* For tlb_finish_mmu */
	int tlb_start_valid = 0;
	unsigned long start = start_addr;
	spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
	int fullmm = tlb_is_full_mm(*tlbp);

	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
		unsigned long end;

		start = max(vma->vm_start, start_addr);
		if (start >= vma->vm_end)
			continue;
		end = min(vma->vm_end, end_addr);
		if (end <= vma->vm_start)
			continue;

		if (vma->vm_flags & VM_ACCOUNT)
			*nr_accounted += (end - start) >> PAGE_SHIFT;

		while (start != end) {
			unsigned long block;

			if (!tlb_start_valid) {
				tlb_start = start;
				tlb_start_valid = 1;
			}

			if (is_vm_hugetlb_page(vma)) {
				block = end - start;
				unmap_hugepage_range(vma, start, end);
			} else {
				block = min(zap_bytes, end - start);
				unmap_page_range(*tlbp, vma, start,
						start + block, details);
			}

			start += block;
			zap_bytes -= block;
			if ((long)zap_bytes > 0)
				continue;

			tlb_finish_mmu(*tlbp, tlb_start, start);

			if (need_resched() ||
				need_lockbreak(&mm->page_table_lock) ||
				(i_mmap_lock && need_lockbreak(i_mmap_lock))) {
				if (i_mmap_lock) {
					/* must reset count of rss freed */
					*tlbp = tlb_gather_mmu(mm, fullmm);
					goto out;
				}
				spin_unlock(&mm->page_table_lock);
				cond_resched();
				spin_lock(&mm->page_table_lock);
			}

			*tlbp = tlb_gather_mmu(mm, fullmm);
			tlb_start_valid = 0;
			zap_bytes = ZAP_BLOCK_SIZE;
		}
	}
out:
	return start;	/* which is now the end (or restart) address */
}

/**
 * zap_page_range - remove user pages in a given range
 * @vma: vm_area_struct holding the applicable pages
 * @address: starting address of pages to zap
 * @size: number of bytes to zap
 * @details: details of nonlinear truncation or shared cache invalidation
 */
unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
		unsigned long size, struct zap_details *details)
{
	struct mm_struct *mm = vma->vm_mm;
	struct mmu_gather *tlb;
	unsigned long end = address + size;
	unsigned long nr_accounted = 0;

	if (is_vm_hugetlb_page(vma)) {
		zap_hugepage_range(vma, address, size);
		return end;
	}

	lru_add_drain();
	spin_lock(&mm->page_table_lock);
	tlb = tlb_gather_mmu(mm, 0);
	end = unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details);
	tlb_finish_mmu(tlb, address, end);
	spin_unlock(&mm->page_table_lock);
	return end;
}

/*
 * Do a quick page-table lookup for a single page.
 * mm->page_table_lock must be held.
 */
static struct page *__follow_page(struct mm_struct *mm, unsigned long address,
			int read, int write, int accessed)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *ptep, pte;
	unsigned long pfn;
	struct page *page;

	page = follow_huge_addr(mm, address, write);
	if (! IS_ERR(page))
		return page;

	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		goto out;

	pud = pud_offset(pgd, address);
	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
		goto out;
	
	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
		goto out;
	if (pmd_huge(*pmd))
		return follow_huge_pmd(mm, address, pmd, write);

	ptep = pte_offset_map(pmd, address);
	if (!ptep)
		goto out;

	pte = *ptep;
	pte_unmap(ptep);
	if (pte_present(pte)) {
		if (write && !pte_write(pte))
			goto out;
		if (read && !pte_read(pte))
			goto out;
		pfn = pte_pfn(pte);
		if (pfn_valid(pfn)) {
			page = pfn_to_page(pfn);
			if (accessed) {
				if (write && !pte_dirty(pte) &&!PageDirty(page))
					set_page_dirty(page);
				mark_page_accessed(page);
			}
			return page;
		}
	}

out:
	return NULL;
}

inline struct page *
follow_page(struct mm_struct *mm, unsigned long address, int write)
{
	return __follow_page(mm, address, 0, write, 1);
}

/*
 * check_user_page_readable() can be called frm niterrupt context by oprofile,
 * so we need to avoid taking any non-irq-safe locks
 */
int check_user_page_readable(struct mm_struct *mm, unsigned long address)
{
	return __follow_page(mm, address, 1, 0, 0) != NULL;
}
EXPORT_SYMBOL(check_user_page_readable);

static inline int
untouched_anonymous_page(struct mm_struct* mm, struct vm_area_struct *vma,
			 unsigned long address)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;

	/* Check if the vma is for an anonymous mapping. */
	if (vma->vm_ops && vma->vm_ops->nopage)
		return 0;

	/* Check if page directory entry exists. */
	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		return 1;

	pud = pud_offset(pgd, address);
	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
		return 1;

	/* Check if page middle directory entry exists. */
	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
		return 1;

	/* There is a pte slot for 'address' in 'mm'. */
	return 0;
}

int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long start, int len, int write, int force,
		struct page **pages, struct vm_area_struct **vmas)
{
	int i;
	unsigned int flags;

	/* 
	 * Require read or write permissions.
	 * If 'force' is set, we only require the "MAY" flags.
	 */
	flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
	flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
	i = 0;

	do {
		struct vm_area_struct *	vma;

		vma = find_extend_vma(mm, start);
		if (!vma && in_gate_area(tsk, start)) {
			unsigned long pg = start & PAGE_MASK;
			struct vm_area_struct *gate_vma = get_gate_vma(tsk);
			pgd_t *pgd;
			pud_t *pud;
			pmd_t *pmd;
			pte_t *pte;
			if (write) /* user gate pages are read-only */
				return i ? : -EFAULT;
			if (pg > TASK_SIZE)
				pgd = pgd_offset_k(pg);
			else
				pgd = pgd_offset_gate(mm, pg);
			BUG_ON(pgd_none(*pgd));
			pud = pud_offset(pgd, pg);
			BUG_ON(pud_none(*pud));
			pmd = pmd_offset(pud, pg);
			if (pmd_none(*pmd))
				return i ? : -EFAULT;
			pte = pte_offset_map(pmd, pg);
			if (pte_none(*pte)) {
				pte_unmap(pte);
				return i ? : -EFAULT;
			}
			if (pages) {
				pages[i] = pte_page(*pte);
				get_page(pages[i]);
			}
			pte_unmap(pte);
			if (vmas)
				vmas[i] = gate_vma;
			i++;
			start += PAGE_SIZE;
			len--;
			continue;
		}

		if (!vma || (vma->vm_flags & VM_IO)
				|| !(flags & vma->vm_flags))
			return i ? : -EFAULT;

		if (is_vm_hugetlb_page(vma)) {
			i = follow_hugetlb_page(mm, vma, pages, vmas,
						&start, &len, i);
			continue;
		}
		spin_lock(&mm->page_table_lock);
		do {
			int write_access = write;
			struct page *page;

			cond_resched_lock(&mm->page_table_lock);
			while (!(page = follow_page(mm, start, write_access))) {
				int ret;

				/*
				 * Shortcut for anonymous pages. We don't want
				 * to force the creation of pages tables for
				 * insanely big anonymously mapped areas that
				 * nobody touched so far. This is important
				 * for doing a core dump for these mappings.
				 */
				if (!write && untouched_anonymous_page(mm,vma,start)) {
					page = ZERO_PAGE(start);
					break;
				}
				spin_unlock(&mm->page_table_lock);
				ret = __handle_mm_fault(mm, vma, start, write_access);

				/*
				 * The VM_FAULT_WRITE bit tells us that do_wp_page has
				 * broken COW when necessary, even if maybe_mkwrite
				 * decided not to set pte_write. We can thus safely do
				 * subsequent page lookups as if they were reads.
				 */
				if (ret & VM_FAULT_WRITE)
					write_access = 0;
				
				switch (ret & ~VM_FAULT_WRITE) {
				case VM_FAULT_MINOR:
					tsk->min_flt++;
					break;
				case VM_FAULT_MAJOR:
					tsk->maj_flt++;
					break;
				case VM_FAULT_SIGBUS:
					return i ? i : -EFAULT;
				case VM_FAULT_OOM:
					return i ? i : -ENOMEM;
				default:
					BUG();
				}
				spin_lock(&mm->page_table_lock);
			}
			if (pages) {
				pages[i] = page;
				flush_dcache_page(page);
				if (!PageReserved(page))
					page_cache_get(page);
			}
			if (vmas)
				vmas[i] = vma;